© 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. 59143
    Prev
    Next
    INDEX
    Explanations

    Batman comics and continuity

    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
    zelf
    -0.11
    æĢ§çĸ¾çĹħ
    -0.10
    isu
    -0.10
    è¹Ī
    -0.10
    ularity
    -0.10
    å®Įæ¯ķ
    -0.09
    è®·
    -0.09
    mmo
    -0.09
    riere
    -0.09
    ../../../
    -0.09
    POSITIVE LOGITS
    /or
    0.09
    olas
    0.08
    ï¸
    0.08
    /IP
    0.08
    ouch
    0.08
    ford
    0.08
    uator
    0.08
    åij¦
    0.07
    æľīä¿¡å¿ĥ
    0.07
    èĿĻ
    0.07
    Activations Density 0.010%

    No Known Activations