© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33125
    Prev
    Next
    INDEX
    Explanations

    rape and sexual assault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.10
    ween
    -0.10
     sÃłng
    -0.09
    arity
    -0.08
    ally
    -0.08
    tle
    -0.08
     Æ¡n
    -0.08
    arily
    -0.08
    Ev
    -0.08
    /people
    -0.08
    POSITIVE LOGITS
    æ°IJ
    0.09
    ety
    0.09
    èĸľ
    0.09
    è¡Įéķ¿
    0.09
    bones
    0.09
    åĽŀé¦ĸ
    0.09
    åIJĦè¡Į
    0.08
    isher
    0.08
    çĻ¸
    0.08
    èĸ®
    0.08
    Activations Density 0.006%

    No Known Activations