© 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. 19934
    Prev
    Next
    INDEX
    Explanations

    percentage changes or statistics

    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
    èİĵ
    -0.11
    åľ°æ¯¯
    -0.10
    æ´»çĿĢ
    -0.10
    èĭ
    -0.09
    terra
    -0.09
    [email
    -0.09
    è¦ģçŁ¥éģĵ
    -0.08
    没éĹ®é¢ĺ
    -0.08
    åħį责声æĺİ
    -0.08
    erer
    -0.08
    POSITIVE LOGITS
    idian
    0.09
    è¿ľç¦»
    0.08
    âĺĥ
    0.08
    éĤ»
    0.08
    poon
    0.08
    ICI
    0.08
    nan
    0.08
     Shar
    0.08
    orts
    0.08
    æĦŁ
    0.08
    Activations Density 0.003%

    No Known Activations