© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    Serena Williams

    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
    tron
    -0.11
    ç¢İ
    -0.11
    èĮ¹
    -0.10
    è´«åĽ°åľ°åĮº
    -0.10
     depths
    -0.10
    深度
    -0.10
    æ¿Ĵ
    -0.10
    温åĴĮ
    -0.10
    achu
    -0.09
    alach
    -0.09
    POSITIVE LOGITS
    åĮ¡
    0.10
    erty
    0.09
    arin
    0.08
    _dirty
    0.08
    åŃij
    0.08
    éĩĩ
    0.08
    æ¡£
    0.08
    jective
    0.07
    æİ¡
    0.07
    ocity
    0.07
    Activations Density 0.003%

    No Known Activations