© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    Arthur followed by names

    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
    åŃIJéĩĮ
    -0.10
    ulates
    -0.09
    _artist
    -0.09
    ä¸įå¤Ł
    -0.09
    sWith
    -0.09
    è¯Ł
    -0.08
    оз
    -0.08
    atory
    -0.08
    ULAR
    -0.08
     Bernardino
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    ../../../
    0.10
    ×ķף
    0.10
    à¹Į
    0.10
    teen
    0.09
    iffs
    0.09
    è·
    0.09
    fully
    0.09
    itus
    0.09
    andom
    0.09
    Activations Density 0.026%

    No Known Activations