© 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. 26956
    Prev
    Next
    INDEX
    Explanations

    bunch of, lot of, ton of

    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
     cape
    -0.09
    ä¸ĢæŃ¥
    -0.09
     Epstein
    -0.08
    _EXTENDED
    -0.08
    chron
    -0.08
    ripp
    -0.08
    å¿ħå®ļ
    -0.08
    èħ¹æ³»
    -0.07
    æŀģå°ij
    -0.07
     Circular
    -0.07
    POSITIVE LOGITS
    åħ¸åŀĭ
    0.10
    åİĿ
    0.10
    æĪĸå¤ļ
    0.10
    éĴŀ
    0.09
    _FWD
    0.09
    æĿĤ
    0.09
    å¢Ł
    0.09
    èµ³
    0.09
    ç»Ħç»ĩå®ŀæĸ½
    0.09
    çł´éŨ
    0.08
    Activations Density 0.016%

    No Known Activations