© 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. 57482
    Prev
    Next
    INDEX
    Explanations

    Sand, Forward, Power, Game, July

    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
    errupt
    -0.10
    ç¾İæ´²
    -0.09
     ÑģлÑĥÑĩаÑı
    -0.08
     IGN
    -0.08
    ÑĢон
    -0.08
    orks
    -0.08
    çŀij
    -0.08
    ç¿Ģ
    -0.08
    æ³Ĺ
    -0.08
    atty
    -0.08
    POSITIVE LOGITS
    纳
    0.11
    éĻįèIJ½
    0.09
    -Za
    0.08
    ç»Į
    0.08
    enen
    0.08
    ç´į
    0.08
    çĽ¼æľĽ
    0.08
    å¸ĮæľĽèĩªå·±
    0.08
     Reed
    0.08
    å¿ĥ头
    0.08
    Activations Density 0.022%

    No Known Activations