© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    false dichotomy or binary states

    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
    eti
    -0.10
    åħļçļĦé¢Ĩ导
    -0.09
    ä¸Ńéĥ¨
    -0.08
    æĬµåĪ¶
    -0.08
    sworth
    -0.08
     пÑĢез
    -0.08
    ׾×Ķ
    -0.08
    FT
    -0.08
    دÙĪ
    -0.08
     Tâm
    -0.08
    POSITIVE LOGITS
    ç®ĢåĮĸ
    0.12
    èĤ¤
    0.10
    åªļ
    0.09
    贵宾
    0.09
    æīĵéĢļ
    0.09
    ä¸įä¸Ĭ
    0.09
    æĽ´å®¹æĺĵ
    0.09
    ç¼®
    0.09
    è°Ģ
    0.09
    appl
    0.08
    Activations Density 0.044%

    No Known Activations