© 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. 17477
    Prev
    Next
    INDEX
    Explanations

    request or asking

    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
    缩
    -0.08
    縮
    -0.07
     abb
    -0.07
    forge
    -0.07
    éħ¸
    -0.07
    eneral
    -0.07
     pharm
    -0.07
    带
    -0.07
     disp
    -0.07
    loor
    -0.07
    POSITIVE LOGITS
    请æ±Ĥ
    0.23
     请æ±Ĥ
    0.21
     request
    0.20
     ìļĶì²Ń
    0.20
     requests
    0.20
    :request
    0.19
    request
    0.18
    .request
    0.18
    è«ĭæ±Ĥ
    0.17
     Requests
    0.17
    Activations Density 0.097%

    No Known Activations