© 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. 27979
    Prev
    Next
    INDEX
    Explanations

    nerve pain, growth, injury, terminals, endings

    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±ĢéĿ¢
    -0.11
    er
    -0.09
    avar
    -0.09
    èĩªä¸»åĵģçīĮ
    -0.08
    ä¼ļåIJĮ
    -0.08
    rix
    -0.08
    éĵİ
    -0.08
    åģıè¿ľ
    -0.08
    elves
    -0.08
    ate
    -0.08
    POSITIVE LOGITS
    lessly
    0.14
    IGATION
    0.10
    icas
    0.09
    деÑģÑıÑĤ
    0.09
    è§ļ
    0.09
    rollo
    0.09
    angelo
    0.09
    less
    0.09
    主任
    0.09
    ULAR
    0.09
    Activations Density 0.038%

    No Known Activations