© 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. 38674
    Prev
    Next
    INDEX
    Explanations

    asking for information

    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
    åĬĿ
    -0.09
    æ¦Ķ
    -0.09
     Newtown
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
     Ma
    -0.08
     nice
    -0.08
     Hack
    -0.08
    Reject
    -0.08
    éģ£
    -0.08
    计æıIJ
    -0.07
    POSITIVE LOGITS
    以便
    0.13
    åħ·ä½ĵæĥħåĨµ
    0.12
    åħ·ä½ĵ
    0.11
    åħ·ä½ĵçļĦ
    0.11
    詳細
    0.10
    æİ¥åĬĽ
    0.10
    è¯ĬæĸŃ
    0.10
    ä¸ĬæĿ¥
    0.09
    çħ³
    0.09
    详ç»Ĩ
    0.09
    Activations Density 0.157%

    No Known Activations