© 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. 26689
    Prev
    Next
    INDEX
    Explanations

    backlight and display enclosure

    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
    _semaphore
    -0.10
    çĻ¾èĬ±
    -0.09
    hir
    -0.09
    åºĩ
    -0.09
    绸
    -0.09
    mast
    -0.08
    åı¯ä»¥çĽ´æİ¥
    -0.08
    iant
    -0.08
    èijµ
    -0.08
     Jian
    -0.08
    POSITIVE LOGITS
    临
    0.10
    ä¸ĩåı°
    0.09
    èĥĮ
    0.09
    itos
    0.09
    ä¸Ģå¼ł
    0.09
    èĥĮçĿĢ
    0.09
    èĢģçĪ¸
    0.08
    ç®Ń
    0.08
    å®īå¨ľ
    0.08
    gs
    0.08
    Activations Density 0.331%

    No Known Activations