© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37253
    Prev
    Next
    INDEX
    Explanations

    languages

    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
    jang
    -0.10
    ATIC
    -0.10
    pez
    -0.10
    eller
    -0.09
    лем
    -0.09
    entr
    -0.08
    edd
    -0.08
    ingt
    -0.08
    人æ°Ķ
    -0.08
     coun
    -0.08
    POSITIVE LOGITS
    èĩ£
    0.10
    åı¯ä»¥å¸®åĬ©
    0.10
    åı¯ä»¥æĽ´å¥½
    0.09
    çĸĻ
    0.09
    é¢Ĩ导干éĥ¨
    0.09
    ä½ľä¸ºä¸Ģç§į
    0.09
    /bus
    0.08
    _fwd
    0.08
    mps
    0.08
    èij£
    0.08
    Activations Density 0.044%

    No Known Activations