© 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. 24000
    Prev
    Next
    INDEX
    Explanations

    daily ritual

    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
     LETTER
    -0.09
    ãģ¡
    -0.09
    çŃ¾çº¦
    -0.09
    éªij
    -0.09
    repid
    -0.09
    åĬłå¿«åıijå±ķ
    -0.08
    hung
    -0.08
    ittal
    -0.08
    ctica
    -0.08
    -ft
    -0.08
    POSITIVE LOGITS
    åĬŁè¯¾
    0.09
    å¡Į
    0.09
    æ¯ı天
    0.09
    诵
    0.09
     ell
    0.09
    é»ĺ
    0.09
    utc
    0.08
    bi
    0.08
    å®Įæķ´çļĦ
    0.08
    æĻ·
    0.08
    Activations Density 0.066%

    No Known Activations