© 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. 19614
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
    stell
    -0.09
    èĪį
    -0.09
    åģ·åģ·
    -0.09
    æį¨
    -0.09
    steller
    -0.09
    akh
    -0.08
     sill
    -0.08
    thur
    -0.08
     Plug
    -0.08
    æ¹į
    -0.08
    POSITIVE LOGITS
    ä¿Ĺ称
    0.09
    æĶ¹éĿ©åıijå±ķ
    0.08
    ä¸Ģåı·
    0.08
    ãģ¨ãĤĤ
    0.08
    天ä¸ĭ
    0.08
    ç®Ģ称
    0.08
    ä¸ĢçĤ¹éĥ½ä¸į
    0.08
    ying
    0.08
    ResponseType
    0.08
    æĪĸèĢħæĺ¯
    0.08
    Activations Density 0.488%

    No Known Activations