© 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. 11357
    Prev
    Next
    INDEX
    Explanations

    urgent need

    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
    enge
    -0.10
    à¸ĩ
    -0.10
    дÑĢ
    -0.09
    àºĩ
    -0.08
    åĺ»åĺ»
    -0.08
    cmb
    -0.08
    à¸Ńà¸ĩ
    -0.08
    ChangeEvent
    -0.08
     долж
    -0.07
    绩
    -0.07
    POSITIVE LOGITS
    紧迫
    0.16
    è¿«
    0.14
    æĢ¥
    0.14
    ness
    0.12
    ente
    0.11
    ency
    0.11
     urg
    0.11
    è¿«åĪĩ
    0.11
    ìĤ¬íķŃ
    0.11
    æĿ¥ä¸įåıĬ
    0.10
    Activations Density 0.014%

    No Known Activations