© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    preventions and outcomes

    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
    åĽ°éļ¾
    -0.08
    éĽĨä½ĵ
    -0.08
    çĸµ
    -0.08
    ç¢į
    -0.08
    宣
    -0.08
    è´¢è¿IJ
    -0.08
    èĽĶ
    -0.07
    åŁĴ
    -0.07
    è¡Į车
    -0.07
    æĬ±çĿĢ
    -0.07
    POSITIVE LOGITS
    çļĦé£Łçī©
    0.10
    è¿ľç¦»
    0.10
     пÑĢоиÑģ
    0.09
    æĻļæľŁ
    0.09
    ç¿»å¼Ģ
    0.09
     gro
    0.09
    çĶŁçī©åѦ
    0.09
    .gl
    0.09
     má
    0.09
    gro
    0.09
    Activations Density 0.060%

    No Known Activations