© 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. 23353
    Prev
    Next
    INDEX
    Explanations

    mutt williams

    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
    ä¾Ī
    -0.10
    iphone
    -0.09
    esi
    -0.09
    äºĶæĺŁ
    -0.09
    icom
    -0.08
    uw
    -0.08
    å¹»æĥ³
    -0.08
    WARE
    -0.08
    èĩ³ä»Ĭ
    -0.08
    vn
    -0.08
    POSITIVE LOGITS
    çĶ³æĬ¥
    0.09
    readOnly
    0.08
     himself
    0.08
    æīĭä¸ĭ
    0.08
    _SCOPE
    0.08
    æĺ¯ä¸ĢåIJį
    0.08
     Hemp
    0.08
    -focus
    0.08
    åı¯åľ¨
    0.07
    èĺ¸
    0.07
    Activations Density 0.073%

    No Known Activations