© 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. 5488
    Prev
    Next
    INDEX
    Explanations

    milestone achievement

    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
    çĤ¯
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    assist
    -0.09
    åijĺ
    -0.09
    hift
    -0.09
    è¾Ļ
    -0.08
    سار
    -0.08
    åĦĨ
    -0.08
    .ParseException
    -0.08
    idis
    -0.08
    POSITIVE LOGITS
    immer
    0.09
    庸
    0.09
    bach
    0.09
    çĦ¶æĺ¯
    0.09
    -grow
    0.09
    å¬ĸ
    0.09
    çľĻ
    0.08
    _THROW
    0.08
    ãĤĬ
    0.08
    ently
    0.08
    Activations Density 0.003%

    No Known Activations