© 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. 24272
    Prev
    Next
    INDEX
    Explanations

    blaze, maze, Hazel name parts

    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
    Negative Logits
    sWith
    -0.13
    çĦ¶æĺ¯
    -0.10
    ваÑĢ
    -0.10
     Dancing
    -0.10
    naire
    -0.10
    standing
    -0.09
    ality
    -0.09
    èĮ§
    -0.09
    shire
    -0.09
    大家åĪĨ享
    -0.09
    POSITIVE LOGITS
    0.14
    è¿ĩåIJİ
    0.10
    ë¡Ń
    0.10
    bourne
    0.09
    holder
    0.09
    -eyed
    0.09
    POINTS
    0.09
    roads
    0.08
    letic
    0.08
    gger
    0.08
    Activations Density 0.008%

    No Known Activations