© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52653
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    åĬŁå¾·
    -0.09
    æĬ¬èµ·
    -0.09
    麻
    -0.08
    ç¿ħ
    -0.08
    ç»ĨèĬĤ
    -0.08
    çĶµæ¢¯
    -0.08
    æŀľå®ŀ
    -0.08
    è¡«
    -0.08
     Larson
    -0.08
    æĬ¬
    -0.08
    POSITIVE LOGITS
    åħ¥èĤ¡
    0.09
    è´Ń
    0.09
    èĪįä¸įå¾Ĺ
    0.09
    å¤ļå¹´çļĦ
    0.09
    æ·ĺæ±°
    0.09
    (optional
    0.08
    <![
    0.08
    èĩ³ä»Ĭ
    0.08
    åħ¼
    0.08
    ç®´
    0.08
    Activations Density 0.240%

    No Known Activations