© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    flash device

    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
     Lamb
    -0.09
     ÑģмÑĭÑģл
    -0.09
     ib
    -0.08
     lamb
    -0.08
    èµ¢
    -0.08
    é»ĺé»ĺåľ°
    -0.08
    åIJĮæł·
    -0.08
    ties
    -0.08
    åIJĮæł·çļĦ
    -0.08
    æļĹ
    -0.08
    POSITIVE LOGITS
    æĿŀ
    0.11
    èĪĴå¿ĥ
    0.11
    æĪIJåijĺåĽ½
    0.10
    ç³ħ
    0.10
     Desmond
    0.09
    umbnail
    0.09
    볨
    0.09
    对å¤ĸ
    0.09
    .getExternal
    0.09
    æªĢ
    0.09
    Activations Density 0.067%

    No Known Activations