© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    I am/can/may

    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
    让æĪij
    -0.10
    è·ŁæĪij
    -0.10
    æĪijå½ĵæŶ
    -0.09
    év
    -0.09
    èĵ¬
    -0.08
    篷
    -0.08
    æĪijéĻ¢
    -0.08
    箪
    -0.08
    使æĪij
    -0.08
    ed
    -0.08
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.10
    è¡Ķ
    0.10
    主è§Ĥ
    0.10
    ç»Ļä½łä»¬
    0.10
    æ²Ķ
    0.09
    åijĬè¯īä½ł
    0.09
    身影
    0.09
    çļĦåĬ¨åĬĽ
    0.09
    ä¼İ
    0.09
    سط
    0.09
    Activations Density 0.099%

    No Known Activations