© 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. 19175
    Prev
    Next
    INDEX
    Explanations

    gene sequences

    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
    宫
    -0.10
    ç¥ŀä»Ļ
    -0.10
     Finch
    -0.10
    kah
    -0.09
    å®®
    -0.09
    esco
    -0.08
    MMC
    -0.08
    æݼ
    -0.08
    pector
    -0.08
    èij
    -0.08
    POSITIVE LOGITS
    å®ļäºĨ
    0.09
    ëĮĢë¡ľ
    0.09
    çīĩ
    0.09
    çīĮ
    0.08
    /exec
    0.08
    çīĩéĿ¢
    0.08
    çĤ¹å¤ļ
    0.08
    ç»ĦåIJĪ
    0.08
    带åĽŀ
    0.08
    åı£æ°´
    0.08
    Activations Density 0.461%

    No Known Activations