© 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. 34408
    Prev
    Next
    INDEX
    Explanations

    unintended consequences or outcomes

    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
    ä¸įåħį
    -0.09
    çľĭä¸įè§ģ
    -0.09
    roe
    -0.09
    æĬ±çĿĢ
    -0.09
    åĨ³è®®
    -0.09
    ä½Ĩæĺ¯åľ¨
    -0.08
    еÑĤе
    -0.08
    å¦Ĥæŀľä¸įæĺ¯
    -0.08
    ingle
    -0.08
    æ¯ķç«Ł
    -0.08
    POSITIVE LOGITS
    åķĨæľº
    0.10
     consequences
    0.09
     consequence
    0.09
    tó
    0.08
    illion
    0.08
    _drawer
    0.08
    Forest
    0.08
     Alarm
    0.08
    èĹIJ
    0.08
    çķĻä¸ĭäºĨ
    0.08
    Activations Density 0.017%

    No Known Activations