© 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. 53535
    Prev
    Next
    INDEX
    Explanations

    closest or near

    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
    ÑĥÑĩа
    -0.08
    èĩªåĪ¶
    -0.08
    uded
    -0.08
    éĢĤæŶ
    -0.08
    æĭ¨
    -0.08
    æĶ»åħ³
    -0.08
    èĢĮåĩº
    -0.08
    mdi
    -0.08
    صد
    -0.08
     Clair
    -0.08
    POSITIVE LOGITS
    æİ¥è¿ij
    0.24
    è´´è¿ij
    0.15
     close
    0.14
    éĢ¼è¿ij
    0.14
    /close
    0.13
    close
    0.13
     closest
    0.13
    (close
    0.12
     Close
    0.12
    éĿłè¿ij
    0.12
    Activations Density 0.075%

    No Known Activations