© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 49323
    Prev
    Next
    INDEX
    Explanations

    maleonitriledithiolate, diallyl maleate

    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
    ansson
    -0.09
    èĢģåŃIJ
    -0.09
    (named
    -0.09
    磮
    -0.08
    ument
    -0.08
    tures
    -0.08
    åīįæıIJ
    -0.08
    seys
    -0.08
    è·ijæŃ¥
    -0.08
    ÑĢова
    -0.08
    POSITIVE LOGITS
    身边çļĦ
    0.09
    ç´ł
    0.09
    符
    0.09
    å¸ĸ
    0.09
     dozens
    0.09
    å··
    0.08
    åijĬè¯ī大家
    0.08
    ç´łè´¨
    0.08
    ç¼¥
    0.08
    åıĻ
    0.08
    Activations Density 0.598%

    No Known Activations