© 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. 56680
    Prev
    Next
    INDEX
    Explanations

    relative locations and proximity

    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
     Brid
    -0.08
     someday
    -0.08
    ç¥ĸåĽ½
    -0.08
     Edition
    -0.08
    _gid
    -0.08
    ä¸ŃåĽ½çļĦ
    -0.08
    æ½ľ
    -0.08
    顽
    -0.08
    биÑĢ
    -0.08
    è¿ĽæĶ»
    -0.07
    POSITIVE LOGITS
    éļıå¤Ħ
    0.11
    å°±è¿ij
    0.10
    åİ»åĮ»éĻ¢
    0.09
    éĿŀ常好çļĦ
    0.09
    临港
    0.09
    çijĻ
    0.09
    åĩłæŃ¥
    0.09
    é¢ĦçķĻ
    0.09
    è¾ĸåĮºåĨħ
    0.09
    ä½Ĩè¿Ļ
    0.08
    Activations Density 0.072%

    No Known Activations