© 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. 36435
    Prev
    Next
    INDEX
    Explanations

    available evidence

    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
    ç¿°
    -0.09
    纬
    -0.09
    ä¸ĢæīĢ
    -0.08
    á»ĭch
    -0.08
    wap
    -0.08
    顺
    -0.07
    æ¸ł
    -0.07
    æŁĵ
    -0.07
    .Cond
    -0.07
    è¿Ļ件äºĭ
    -0.07
    POSITIVE LOGITS
    对ä»ĸ们
    0.11
    available
    0.11
     available
    0.10
    atori
    0.10
    åı¯çĶ¨
    0.10
    -available
    0.10
     Accent
    0.10
    éĢļè¡Į
    0.10
     disponÃŃveis
    0.09
    主æµģ
    0.09
    Activations Density 0.092%

    No Known Activations