© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    rowing and 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
    emes
    -0.09
    蹶
    -0.09
    алÑĮ
    -0.09
     Dra
    -0.09
    amel
    -0.08
    lite
    -0.08
    ced
    -0.08
    象
    -0.08
    pin
    -0.08
    å²Ń
    -0.08
    POSITIVE LOGITS
    ëĿ½
    0.10
    ãĢħ
    0.10
    idl
    0.09
    éĿ
    0.09
    车åºĵ
    0.09
    ldb
    0.08
    ivent
    0.08
    æ¼Ĩ
    0.08
     ëĭ¨
    0.08
     Kı
    0.08
    Activations Density 0.006%

    No Known Activations