© 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. 40046
    Prev
    Next
    INDEX
    Explanations

    added to

    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
    isque
    -0.10
    unker
    -0.10
    è¡Ŀ
    -0.09
    ussed
    -0.09
    ifferent
    -0.09
    iams
    -0.09
    ноÑģÑĤей
    -0.09
    untime
    -0.09
    ieber
    -0.09
    otime
    -0.09
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.19
    çİ°æľīçļĦ
    0.18
    åİŁæľī
    0.14
     existing
    0.13
    åĴĮå®ĮåĸĦ
    0.13
    çİ°æľī
    0.13
    existing
    0.12
     Existing
    0.11
    åİŁæĿ¥çļĦ
    0.10
    å·²ç»ıæľī
    0.10
    Activations Density 0.062%

    No Known Activations