© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34509
    Prev
    Next
    INDEX
    Explanations

    island

    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
    Ùij
    -0.11
    æªĶ
    -0.09
     wol
    -0.09
    dk
    -0.09
    asper
    -0.09
    outer
    -0.09
    å¥Ĥ
    -0.08
    åľºéĿ¢
    -0.08
    ToDo
    -0.08
    tings
    -0.08
    POSITIVE LOGITS
    å²Ľ
    0.10
    竦
    0.09
    æ²IJ
    0.09
    (Is
    0.09
    å¶
    0.09
    updates
    0.08
    /is
    0.08
    ÙĬÙĤ
    0.08
    ä¸ĬçļĦ
    0.08
    島
    0.08
    Activations Density 0.028%

    No Known Activations