© 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. 35685
    Prev
    Next
    INDEX
    Explanations

    safely installing or refactoring

    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
    ä¼ĺ
    -0.11
    壹
    -0.10
    çªł
    -0.09
    ç§įåŃIJ
    -0.09
    ụ
    -0.09
    getStatus
    -0.09
    FunctionFlags
    -0.09
    owered
    -0.09
    chal
    -0.09
    DIRECTORY
    -0.09
    POSITIVE LOGITS
    æħİéĩį
    0.15
    è°¨æħİ
    0.14
    å°ıå¿ĥ翼翼
    0.14
    7
    0.12
    8
    0.12
    6
    0.12
    9
    0.12
    0
    0.11
    4
    0.11
     irreversible
    0.11
    Activations Density 0.155%

    No Known Activations