© 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. 11204
    Prev
    Next
    INDEX
    Explanations

    black anchor

    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
     rejo
    -0.10
    æĪij们认为
    -0.10
    å®ĺ
    -0.09
     doc
    -0.09
    å¨ģ
    -0.08
    çĪ±ä½ł
    -0.08
    èĩªä¿¡
    -0.08
    erg
    -0.08
     Serg
    -0.08
    obot
    -0.08
    POSITIVE LOGITS
    é»ĺ
    0.12
    å¥ł
    0.11
    ç¥Ń
    0.10
    ç¼ħ
    0.10
    æĤ¼
    0.10
    è¯Ķ
    0.10
    aunch
    0.09
     Visitors
    0.09
    èĤĥ
    0.09
    å¯Ħæīĺ
    0.09
    Activations Density 0.054%

    No Known Activations