© 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. 49536
    Prev
    Next
    INDEX
    Explanations

    violence against

    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
    olicies
    -0.09
     Reese
    -0.09
    langs
    -0.09
     bè
    -0.08
    ivers
    -0.08
    åŃIJéĩĮ
    -0.08
    erin
    -0.08
    scription
    -0.08
    èĩ¾
    -0.08
    çĤİ
    -0.08
    POSITIVE LOGITS
    -minded
    0.11
    è¢Ń
    0.10
    第ä¸ĢæŃ¥
    0.10
    alse
    0.10
    cly
    0.09
    ous
    0.09
    ened
    0.09
     hạt
    0.08
    ħ
    0.08
    è¡Ģèħ¥
    0.08
    Activations Density 0.014%

    No Known Activations