© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    council or congress names

    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
    ãģ¶
    -0.10
    åİ¿åħ¬å®īå±Ģ
    -0.10
    ilda
    -0.09
    ITES
    -0.09
    ä¾Ľå¤§å®¶
    -0.09
    æĶ¿åħļ
    -0.09
    èĥĻ
    -0.08
    éĹ³
    -0.08
    èĭįçĻ½
    -0.08
    æĭĽèĤ¡
    -0.08
    POSITIVE LOGITS
    ABI
    0.10
     councils
    0.09
     council
    0.09
    ouncil
    0.09
    pps
    0.08
    å§Ķåijĺ
    0.08
    åijĬ
    0.08
    åĹŁ
    0.08
    plib
    0.08
    ä¸ĢåĽ¢
    0.08
    Activations Density 0.018%

    No Known Activations