© 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. 5518
    Prev
    Next
    INDEX
    Explanations

    representative answering calls/phones

    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
    /Private
    -0.10
    éĩijèŀįæľºæŀĦ
    -0.09
    åIJĬ
    -0.09
    åĬ¨åijĺ
    -0.09
    LECTION
    -0.09
    .native
    -0.09
    _EVT
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    å§Ķç»Ħç»ĩ
    -0.08
    åIJĪä½ľä¼Ļä¼´
    -0.08
    POSITIVE LOGITS
    åIJįåı«
    0.10
    åĪĨ管
    0.10
    ç¡
    0.09
    主管
    0.09
    è´Łè´£
    0.09
    è¶Ĭ
    0.09
    -sales
    0.09
    éļ¶å±ŀäºİ
    0.09
    овиÑĩ
    0.09
     cÃłng
    0.09
    Activations Density 0.060%

    No Known Activations