© 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. 31517
    Prev
    Next
    INDEX
    Explanations

    important, answer, different kinds

    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
    åĮ¹éħį
    -0.08
    ç»ĵåIJĪèµ·æĿ¥
    -0.08
    ä¸Ģä¸Ģ
    -0.07
    è§ģéĿ¢
    -0.07
    ilet
    -0.07
    un
    -0.07
     Rational
    -0.07
    纵
    -0.07
    åIJĮèĥŀ
    -0.07
    unny
    -0.07
    POSITIVE LOGITS
    /LICENSE
    0.09
    榫
    0.09
    emat
    0.09
    æ¾Ħæ¸ħ
    0.08
    imary
    0.08
    chter
    0.08
    PropertyValue
    0.08
    rü
    0.08
    è¿Ľåħ¥åĪ°
    0.08
    _TP
    0.08
    Activations Density 0.079%

    No Known Activations