© 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. 36148
    Prev
    Next
    INDEX
    Explanations

    /suggestion

    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
    çĦ¶æĺ¯
    -0.12
    UEST
    -0.10
    RIES
    -0.10
    гон
    -0.10
    ynchron
    -0.09
    横
    -0.09
    .Std
    -0.09
    PECT
    -0.09
    ä¿Ŀ管
    -0.09
    éĥ½çŁ¥éģĵ
    -0.09
    POSITIVE LOGITS
    ly
    0.12
    ำ
    0.10
    an
    0.10
    åIJĦæł·
    0.10
    gether
    0.09
    0
    0.09
    ed
    0.09
    zelf
    0.09
     Hamp
    0.09
    2
    0.09
    Activations Density 0.360%

    No Known Activations