© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 55304
    Prev
    Next
    INDEX
    Explanations

    The neuron detects explicit sexual content—detailed descriptions of sexual body parts, acts, sensations, and erotic behavior.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    毀
    -0.07
     birth
    -0.07
    /router
    -0.07
     arrow
    -0.07
     hex
    -0.07
    _CPU
    -0.06
     retrieval
    -0.06
    .show
    -0.06
    -collection
    -0.06
     evacuate
    -0.06
    POSITIVE LOGITS
    warm
    0.07
     Rewards
    0.07
    챈
    0.07
     Während
    0.07
    开朗
    0.07
     NATO
    0.07
     Costa
    0.07
    otel
    0.07
    semantic
    0.07
     zal
    0.06
    Activations Density 1.494%

    No Known Activations