© 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. 57918
    Prev
    Next
    INDEX
    Explanations

    units of weight

    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
    å°ģ
    -0.09
    é¢Ĩ
    -0.09
    (mid
    -0.09
    å±ģ
    -0.08
    -proof
    -0.08
    æľ¬ç½ij
    -0.08
     Hoe
    -0.08
    äºĮ代
    -0.08
     oversh
    -0.08
    intern
    -0.08
    POSITIVE LOGITS
    åłĨ
    0.10
    ajor
    0.09
    åı¤ä»Ĭ
    0.09
     HEAP
    0.09
    DOWN
    0.08
    ç¼Ł
    0.08
    éĢģç»Ļ
    0.08
    åĮĸèĤ¥
    0.08
    æĮ¤
    0.08
    weit
    0.08
    Activations Density 0.030%

    No Known Activations