© 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. 4676
    Prev
    Next
    INDEX
    Explanations

    first derivative 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
    åīįæīĢ
    -0.09
    åij³
    -0.09
    桤
    -0.08
    ulen
    -0.08
    rtc
    -0.08
    对æĸ¹
    -0.08
     Twig
    -0.08
     акÑĤÑĥ
    -0.08
    izi
    -0.08
    èł¡
    -0.08
    POSITIVE LOGITS
    ä¸ŃåİŁ
    0.10
    shadow
    0.09
    å®ŀåľ¨æĺ¯
    0.09
    plash
    0.09
    é¢ı
    0.09
    çł´
    0.08
    ç³ľ
    0.08
    å®ŀåľ¨
    0.08
    æİĪ
    0.08
    åIJ¸åıĸ
    0.08
    Activations Density 0.106%

    No Known Activations