© 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. 987
    Prev
    Next
    INDEX
    Explanations

    league tables

    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
    å°¼äºļ
    -0.12
    ãģģ
    -0.09
    è®®æ¡Ī
    -0.09
    é«®
    -0.08
    elle
    -0.08
     пÑĢиÑĩ
    -0.08
    поÑĩ
    -0.08
    çĵ¯
    -0.08
    oku
    -0.08
    æĿĥçĽĬ
    -0.08
    POSITIVE LOGITS
    ster
    0.11
    ester
    0.10
    igh
    0.10
    转载请
    0.10
    æĻļæľŁ
    0.10
    æīĵä»Ĺ
    0.10
    orde
    0.09
    sters
    0.09
    istory
    0.09
    isure
    0.09
    Activations Density 0.029%

    No Known Activations