© 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. 19419
    Prev
    Next
    INDEX
    Explanations

    net followed by common suffixes

    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
    åĮ»åѦéĻ¢
    -0.09
    èººåľ¨
    -0.09
    arshal
    -0.09
    sed
    -0.09
    æĻ¯å¾·
    -0.08
    æ®ĩ
    -0.08
    çŃ®
    -0.08
    æµģéĢļ
    -0.08
    çĤ¹åĩ»æŁ¥çľĭ
    -0.08
     tÃŃn
    -0.08
    POSITIVE LOGITS
    lify
    0.10
    大海
    0.09
    大åݦ
    0.09
    /OR
    0.09
    åijĺ
    0.08
    好象
    0.08
    éģįå¸ĥ
    0.08
    为人
    0.08
    缦
    0.08
    eker
    0.08
    Activations Density 0.030%

    No Known Activations