© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12125
    Prev
    Next
    INDEX
    Explanations

    especially when

    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
    ãģ¨ãģ«ãģĭãģı
    -0.10
    è¦ģä¹Ī
    -0.09
     вполне
    -0.09
    ST
    -0.08
    鸱
    -0.08
    _hal
    -0.08
    ä¸įéĶĪ
    -0.08
     ech
    -0.07
     either
    -0.07
    -man
    -0.07
    POSITIVE LOGITS
    _fence
    0.10
    æĺ¯ä»İ
    0.09
    TRIES
    0.09
    (runtime
    0.09
    IDI
    0.09
    称ä¹ĭ
    0.09
    AILS
    0.09
    .mods
    0.09
    è¿ĺè¦ģ
    0.08
    çħľ
    0.08
    Activations Density 0.033%

    No Known Activations