© 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. 61146
    Prev
    Next
    INDEX
    Explanations

    finish or completing tasks

    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
    å¤įæŁ¥
    -0.09
    ä¸Ģå¤ľ
    -0.09
    ãĤ¸ãĥ¥
    -0.09
    éĩįéĩį
    -0.09
    CancelButton
    -0.08
    æĵĤ
    -0.08
    DDL
    -0.08
    èıĺ
    -0.08
    emet
    -0.08
    arding
    -0.08
    POSITIVE LOGITS
    inline
    0.09
    ÑĤон
    0.09
    uel
    0.09
    åºĸ
    0.09
     дело
    0.09
    ery
    0.08
    isch
    0.08
     Cla
    0.08
    åıij表äºĨ
    0.08
     Finished
    0.08
    Activations Density 0.039%

    No Known Activations