© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50758
    Prev
    Next
    INDEX
    Explanations

    sturdy, built, heavy-duty, strong, exterior

    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
    å¼ĢæĿ¥
    -0.12
    lea
    -0.11
    æ¯Ķä¸Ĭå¹´
    -0.09
    åľ£è¯ŀèĬĤ
    -0.09
    overs
    -0.09
    温馨
    -0.09
    robe
    -0.09
    krit
    -0.09
    大åħ¨
    -0.09
    水墨
    -0.09
    POSITIVE LOGITS
    åĿļ硬
    0.10
     дÑĥÑħ
    0.09
    erness
    0.09
    aned
    0.09
    ,strong
    0.09
    è¾ĥ强çļĦ
    0.09
    aho
    0.09
    enson
    0.09
    strong
    0.09
     shining
    0.09
    Activations Density 0.077%

    No Known Activations