© 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. 11347
    Prev
    Next
    INDEX
    Explanations

    Wilhelm, Wilton

    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
    å³Ļ
    -0.12
    éĤij
    -0.11
    æľ¬ç½ij
    -0.11
    é¢ĦåijĬ
    -0.10
    åħļåĨħ
    -0.09
    تÙħ
    -0.09
    .WARNING
    -0.09
    äºĮ代
    -0.09
    çģ
    -0.09
    elage
    -0.09
    POSITIVE LOGITS
    enstein
    0.08
    usal
    0.08
    inox
    0.08
     =>
    0.08
    us
    0.07
    ing
    0.07
    ↵
    0.07
    isz
    0.07
    èĥ¯
    0.07
    im
    0.07
    Activations Density 0.016%

    No Known Activations