© 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. 59125
    Prev
    Next
    INDEX
    Explanations

    making claims or statements

    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
    è¿ĻäºĽä¸ľè¥¿
    -0.10
    andin
    -0.09
    oice
    -0.09
     вли
    -0.09
    ç»ij
    -0.08
     cele
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    RuleContext
    -0.08
    è¿ĻäºĽéĹ®é¢ĺ
    -0.08
    åĨµä¸Ķ
    -0.08
    POSITIVE LOGITS
    溢
    0.11
    æĤ¨åIJĮæĦı
    0.11
    åĩĨç¡®æĢ§
    0.11
    å½ĵä¹ĭæĹłæĦ§
    0.10
    è´´
    0.10
    æıIJåIJį
    0.10
    åĸ³
    0.10
    uÅŁ
    0.09
    骢
    0.09
    髦
    0.09
    Activations Density 0.063%

    No Known Activations