© 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. 34268
    Prev
    Next
    INDEX
    Explanations

    bishop of

    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
    ous
    -0.10
    EST
    -0.10
    é¢Ĩ导人
    -0.09
    ummy
    -0.09
    er
    -0.09
    t
    -0.09
    ä½ĵä¼ļ
    -0.08
    appy
    -0.08
     Stark
    -0.08
    mpp
    -0.08
    POSITIVE LOGITS
    grass
    0.11
    ëĭĺ
    0.10
    /her
    0.10
    esian
    0.09
    éĵĽ
    0.09
    кÑĢаÑĤ
    0.09
    볨
    0.09
    erial
    0.09
    å¨ĺå¨ĺ
    0.09
     conte
    0.09
    Activations Density 0.019%

    No Known Activations