© 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. 3043
    Prev
    Next
    INDEX
    Explanations

    names like Matt, George, Samuel

    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
    _framework
    -0.08
    LEGAL
    -0.08
    ODY
    -0.08
    åĨ°åĨ·
    -0.08
    ç¢į
    -0.08
    à¹Ĥรà¸ĩà¸ŀ
    -0.08
    åį°
    -0.08
    ä»İ严治
    -0.08
    į°
    -0.08
    ctica
    -0.08
    POSITIVE LOGITS
    追赶
    0.10
    ä¸Ģæ¢Ŀ
    0.09
    ób
    0.08
    anian
    0.08
    åį³æŶ
    0.08
    ä»Ģä¹Īåij¢
    0.08
    ÂŃi
    0.08
    ÂŃs
    0.08
    ä¹ĭæĹħ
    0.08
    -headed
    0.08
    Activations Density 0.276%

    No Known Activations