© 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. 62342
    Prev
    Next
    INDEX
    Explanations

    danger, threat, risk

    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
    æĪĺçķ¥åIJĪä½ľ
    -0.09
    æ·Ģ
    -0.09
    dur
    -0.09
    帮å¿Ļ
    -0.09
     Bras
    -0.08
    erus
    -0.08
    jmp
    -0.08
    beg
    -0.08
    ellation
    -0.08
    女主
    -0.08
    POSITIVE LOGITS
    éļıæŶ
    0.12
     imminent
    0.11
    å¿«è¦ģ
    0.11
    éĿ¢ä¸´
    0.10
    å²Į
    0.10
    igar
    0.10
    assa
    0.09
    å¦Ĥæŀľä¸į
    0.09
    éĻIJæľŁ
    0.09
    çĥĽ
    0.09
    Activations Density 0.037%

    No Known Activations