© 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. 35778
    Prev
    Next
    INDEX
    Explanations

    cloud computing services

    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
    ä¸ĢåĪĢ
    -0.10
    _FAR
    -0.10
     Grave
    -0.10
    ä¸ĭæĿ¥çļĦ
    -0.10
    åŁºéĩij份é¢Ŀ
    -0.10
    olan
    -0.09
    .createFrom
    -0.09
    æĢ§çļĦ
    -0.09
    xDC
    -0.09
    沿线
    -0.09
    POSITIVE LOGITS
    æ´±
    0.10
     vap
    0.08
     vapor
    0.08
    äºij
    0.08
     cloud
    0.08
    vely
    0.08
    æ»Ł
    0.08
     ná»ķi
    0.08
    inqu
    0.08
    æĵİ
    0.07
    Activations Density 0.022%

    No Known Activations