© 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. 49852
    Prev
    Next
    INDEX
    Explanations

    non-latin characters

    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
    ìĵ°
    -0.09
    asers
    -0.09
    ANGLES
    -0.08
    èĢķ
    -0.08
     же
    -0.08
    åİĨå¹´
    -0.08
    INET
    -0.08
    UTO
    -0.08
    ä¸įè¿ľ
    -0.08
    singleton
    -0.08
    POSITIVE LOGITS
    æĮĩæݧ
    0.10
    æļĹ示
    0.09
    éĩĮéĿ¢æľī
    0.09
    ç¼ł
    0.08
    责任人
    0.08
    没èĥ½
    0.08
    åħ¸åŀĭçļĦ
    0.08
    梢
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    è¹ī
    0.08
    Activations Density 0.105%

    No Known Activations