© 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. 22803
    Prev
    Next
    INDEX
    Explanations

    crazy month

    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
     Khal
    -0.09
    æĹłå£°
    -0.09
    å¯Ł
    -0.09
    å¯Łçľĭ
    -0.08
    人家
    -0.08
    åı¹æģ¯
    -0.08
    arius
    -0.08
    ç¾İãģĹãģĦ
    -0.08
    åĭĸ
    -0.08
    罩
    -0.08
    POSITIVE LOGITS
    æĥ³è±¡åĬĽ
    0.11
    é£ŀæī¬
    0.10
    å¦Ħ
    0.10
    èĪ¸
    0.10
    念头
    0.10
    èĥ½æĬĬ
    0.09
    æĢª
    0.09
    çĭ·
    0.09
    ä¹İ
    0.09
    æĭ
    0.09
    Activations Density 0.142%

    No Known Activations