© 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. 1448
    Prev
    Next
    INDEX
    Explanations

    exile and reparations

    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
    odash
    -0.09
    èĢĮåİ»
    -0.09
    GEST
    -0.09
    éħ¬
    -0.09
     Mens
    -0.09
    æį¢
    -0.09
    衾
    -0.08
    泯
    -0.08
    è¡®
    -0.08
    .SYSTEM
    -0.08
    POSITIVE LOGITS
    åŁŃ
    0.09
     exile
    0.09
    èµĸ以
    0.09
    éĩį建
    0.09
    ç¥ĸåħĪ
    0.09
    JSONObject
    0.08
    éĻ¢åŃIJ
    0.08
    æľĢéĩįè¦ģ
    0.08
    /doc
    0.08
    åŁİå¢Ļ
    0.08
    Activations Density 0.061%

    No Known Activations