© 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. 30839
    Prev
    Next
    INDEX
    Explanations

    airfoil, spats, span fin, fly over

    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
    丸
    -0.10
    ç¾Į
    -0.09
     вÑĭполнен
    -0.09
    羯
    -0.09
    éĨª
    -0.09
    zes
    -0.08
    license
    -0.08
    åģļå®Į
    -0.08
    æľĢåŁºæľ¬
    -0.08
    inish
    -0.08
    POSITIVE LOGITS
    ç¿
    0.09
    é«ĺ楼
    0.09
    平稳
    0.09
    缴åįĩ
    0.09
    _CERT
    0.09
    ظÙĩ
    0.09
    NIL
    0.09
    å·®è·Ŀ
    0.09
    åij
    0.09
    wil
    0.09
    Activations Density 0.072%

    No Known Activations