© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63373
    Prev
    Next
    INDEX
    Explanations

    references to pornography and the adult entertainment industry, flagging sexual/erotic content and contexts.

    oai_token-act-pair · gpt-5Triggered 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
     surveys
    -0.07
    DM
    -0.07
    IQ
    -0.06
     ра�
    -0.06
     undefeated
    -0.06
     binge
    -0.06
     Survey
    -0.06
    氢能
    -0.06
     Dragons
    -0.06
    能源
    -0.06
    POSITIVE LOGITS
     completo
    0.08
    çu
    0.08
    0.07
    安定
    0.07
    vecs
    0.07
    Installation
    0.07
    =cut
    0.07
    ثبت
    0.06
    וצר
    0.06
     đỡ
    0.06
    Activations Density 0.559%

    No Known Activations