© 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. 5140
    Prev
    Next
    INDEX
    Explanations

    date calculation

    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
    å¥
    -0.08
    [color
    -0.08
    註
    -0.08
     opr
    -0.08
    对该
    -0.08
    çijģ
    -0.08
    æ¥Ķ
    -0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.08
    èĦĸ
    -0.08
    èĶij
    -0.08
    POSITIVE LOGITS
    ofday
    0.10
    ä¼Ļä¼´
    0.09
    ä¸įç¡®å®ļ
    0.09
    çªģåıij
    0.09
    عÙĬÙĨ
    0.09
    ä¼ī
    0.08
    cheduler
    0.08
    è¡£æľį
    0.08
    anye
    0.08
    osta
    0.08
    Activations Density 0.254%

    No Known Activations