© 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. 40155
    Prev
    Next
    INDEX
    Explanations

    produce or create

    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
    èıĢ
    -0.09
    åĬ±
    -0.09
    atee
    -0.08
    éĶ·
    -0.08
    .ascii
    -0.08
     Expression
    -0.08
    解æŀIJ
    -0.08
     Gesture
    -0.08
    itol
    -0.08
    责任ç¼ĸè¾ij
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.19
    产åĩº
    0.16
    åĩºåĵģ
    0.16
    åĩºä¾Ĩ
    0.15
    åĩºäºĨ
    0.15
    åĩºæĿ¥
    0.14
     produ
    0.14
    åĪĽéĢłåĩº
    0.14
    åĩºãģĻ
    0.13
    produ
    0.13
    Activations Density 0.081%

    No Known Activations