© 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. 3552
    Prev
    Next
    INDEX
    Explanations

    questions about

    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
    ä¸ĢåĪĢ
    -0.10
    nable
    -0.09
    æľīæľºä¼ļ
    -0.08
    å°Ŀ
    -0.08
    ogi
    -0.08
    åģļ大
    -0.08
    äºī龸
    -0.07
    caps
    -0.07
    layer
    -0.07
    第äºĮ次
    -0.07
    POSITIVE LOGITS
    åĽ¢éķ¿
    0.10
    诸å¦Ĥ
    0.10
    (Parcel
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
    ervers
    0.09
    è´
    0.09
    å½ĵäºĭ
    0.09
    igor
    0.09
    履约
    0.09
    è¨
    0.08
    Activations Density 0.026%

    No Known Activations