© 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. 57544
    Prev
    Next
    INDEX
    Explanations

    pagan, welfare, summary, rotations, news

    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
    CBS
    -0.10
    家åĸ»æĪ·æĻĵ
    -0.08
    loaded
    -0.08
    à¸ķรา
    -0.08
    uffers
    -0.08
    管
    -0.08
     CBS
    -0.08
    xious
    -0.08
    olvable
    -0.08
    è·Ł
    -0.08
    POSITIVE LOGITS
    ä¸įå¾Ĺ转载
    0.10
    çĩĶ
    0.10
    ç³ģ
    0.09
    åı¤äºº
    0.09
    纪å§Ķ
    0.09
     Apprentice
    0.09
    é»į
    0.09
    æ³Ķ
    0.09
    éĥ¢
    0.08
    访
    0.08
    Activations Density 0.106%

    No Known Activations