© 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. 62913
    Prev
    Next
    INDEX
    Explanations

    colon followed by the

    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
    acob
    -0.09
    èĥ½æĬĬ
    -0.08
    .fd
    -0.08
    Apart
    -0.08
    lem
    -0.08
    çķĢ
    -0.08
    åĬŁ
    -0.08
    å¹´ä¹ĭ
    -0.08
    _except
    -0.08
    è¿Ļéĥ¨
    -0.08
    POSITIVE LOGITS
     ведÑĮ
    0.10
    ãģĹãģ¦ãĤĤ
    0.09
    furt
    0.09
    ä¼ļåIJĮ
    0.08
    icut
    0.08
    æ¯ķç«Ł
    0.08
    fra
    0.08
    unate
    0.08
    _BUFF
    0.08
    ãģłãģ£ãģ¦
    0.08
    Activations Density 0.160%

    No Known Activations