© 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. 34113
    Prev
    Next
    INDEX
    Explanations

    activities and common phrases

    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
    ä½łçİ°åľ¨
    -0.12
    ä½łéľĢè¦ģ
    -0.12
    ç»ĻæĤ¨
    -0.11
    çŁ¥éģĵèĩªå·±
    -0.11
    åĩºå·®
    -0.11
    æį£
    -0.11
    黾
    -0.11
    ç»Ļä½ł
    -0.11
    ä¸ºä½ł
    -0.10
    è¿Īåĩº
    -0.10
    POSITIVE LOGITS
    éĢĹ
    0.09
    GetString
    0.08
    erval
    0.08
     Birth
    0.08
    å±ķ示äºĨ
    0.08
    ps
    0.08
    äºĨä¸Ģä¼ļ
    0.08
    .GetString
    0.08
    åģļäºĨ
    0.08
     briefly
    0.08
    Activations Density 0.047%

    No Known Activations