© 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. 6564
    Prev
    Next
    INDEX
    Explanations

    Jackson Name

    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
    lessly
    -0.11
     hẳn
    -0.10
    afen
    -0.10
    ĵ
    -0.09
    åĸ±
    -0.09
     ÐIJлекÑģан
    -0.09
    ï¸ı
    -0.08
    tre
    -0.08
    isman
    -0.08
    elves
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¾
    0.11
    ry
    0.10
    ively
    0.10
    åĬŀäºĭå¤Ħ
    0.09
    most
    0.09
    lık
    0.09
    ãģĦãģ¾ãģĻ
    0.09
    ей
    0.09
    azzi
    0.09
    ses
    0.09
    Activations Density 0.029%

    No Known Activations