© 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. 61456
    Prev
    Next
    INDEX
    Explanations

    university names departments

    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
     guild
    -0.08
    æłĩæĿĨ
    -0.08
     bride
    -0.08
    æ¹¾åĮº
    -0.07
     Cabr
    -0.07
    IZ
    -0.07
    èĨĿ
    -0.07
    é¥ķ
    -0.07
    å¦Ĥä½ķåİ»
    -0.07
    饵
    -0.07
    POSITIVE LOGITS
    çļĦèīºæľ¯
    0.09
    RAND
    0.09
    auf
    0.09
    .adv
    0.09
    PAL
    0.08
    PLACE
    0.08
    acci
    0.08
    rends
    0.08
    审议
    0.08
    ẩ
    0.08
    Activations Density 0.044%

    No Known Activations