© 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. 5098
    Prev
    Next
    INDEX
    Explanations

    except for

    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
    ä¸Ģæĸ¹éĿ¢
    -0.10
    åį´ä¸į
    -0.10
    èĻ½çĦ¶
    -0.09
    åı¯ä¸įæĺ¯
    -0.09
    atk
    -0.08
    èĻ½
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    vious
    -0.08
    ourt
    -0.08
    æģ°å¥½
    -0.08
    POSITIVE LOGITS
    åIJ¦åĪĻ
    0.11
    æľ´ç´ł
    0.10
    elsen
    0.10
    åIJ¦åīĩ
    0.10
    _else
    0.10
    åı¯ä»¥è¯´
    0.09
     OTHERWISE
    0.09
    æĥħåĨµä¸ĭ
    0.09
    车ä¸Ĭ
    0.09
    uela
    0.09
    Activations Density 0.087%

    No Known Activations