© 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. 59382
    Prev
    Next
    INDEX
    Explanations

    mentions of religions and religious traditions, especially references to “religion(s)” and names of faiths (often with the -ism suffix).

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    Compile
    -0.08
    iece
    -0.07
     partially
    -0.07
    (send
    -0.07
    _accepted
    -0.06
     שאת
    -0.06
    ата
    -0.06
    iseum
    -0.06
    ских
    -0.06
    oteca
    -0.06
    POSITIVE LOGITS
    _measurement
    0.07
    DidChange
    0.07
    Sİ
    0.07
    }>
    0.07
    landırma
    0.07
    让消费者
    0.07
     educación
    0.07
    bard
    0.06
    表述
    0.06
    -position
    0.06
    Activations Density 0.041%

    No Known Activations