© 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. 30318
    Prev
    Next
    INDEX
    Explanations

    other [noun]

    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
    nable
    -0.11
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.10
     counterpart
    -0.10
    æŁIJç§į
    -0.10
    æŁIJäºĽ
    -0.10
    ses
    -0.09
     أخرÙī
    -0.09
    undry
    -0.09
    SES
    -0.09
    ä¹ĭæĹħ
    -0.09
    POSITIVE LOGITS
    -than
    0.15
    world
    0.15
    ç±»åŀĭçļĦ
    0.13
    /new
    0.12
    /all
    0.11
    æĺŁçIJĥ
    0.11
    than
    0.10
    ãĢħ
    0.10
    æ§Ĭ
    0.10
    wis
    0.10
    Activations Density 0.137%

    No Known Activations