© 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. 62789
    Prev
    Next
    INDEX
    Explanations

    database and data technologies

    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
    åīľ
    -0.10
    ä¸ĢçĤ¹çĤ¹
    -0.09
    æĸĮ
    -0.09
    诰
    -0.09
     Win
    -0.09
    Win
    -0.09
    åħij
    -0.09
    置身
    -0.08
    íĻį
    -0.08
    (TokenType
    -0.08
    POSITIVE LOGITS
    滩
    0.09
     Titan
    0.09
    æ²Ļ滩
    0.08
    tweet
    0.08
    /document
    0.08
    å®Ļ
    0.08
    å®Ľ
    0.08
    æľªæĿ¥çļĦ
    0.08
    Americ
    0.08
    æ¼ł
    0.08
    Activations Density 0.407%

    No Known Activations