© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52785
    Prev
    Next
    INDEX
    Explanations

    cost or time units

    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
    离
    -0.10
    éĮ¢
    -0.09
    _FUN
    -0.09
     tal
    -0.09
    åľ£è¯ŀ
    -0.08
    éĽ¢
    -0.08
    éĿĴå°ijå¹´
    -0.08
    æĸ°æĹ¶æľŁ
    -0.08
    æĹ¢èĥ½
    -0.08
     cud
    -0.08
    POSITIVE LOGITS
    代
    0.09
    åĬ³åĬ¡
    0.09
    çªĴ
    0.08
    修为
    0.08
     Ritch
    0.08
     Sanford
    0.08
    _BUF
    0.08
    BUF
    0.08
    éķ¿çŁŃ
    0.08
    å¨ģ
    0.08
    Activations Density 0.096%

    No Known Activations