© 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. 53686
    Prev
    Next
    INDEX
    Explanations

    Ryan Gosling, Murphy, Gosnell

    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
    èݨ
    -0.10
    ç¬ij声
    -0.10
    iday
    -0.09
    -fw
    -0.09
    ä¸Ģå¾ĭ
    -0.09
    æīĭæĦŁ
    -0.09
    ä¸įåı¯ç¼ºå°ij
    -0.09
    åĪĩå°Ķ
    -0.09
    ç¬ijèĦ¸
    -0.09
    ersh
    -0.09
    POSITIVE LOGITS
    åĩĿ
    0.10
    astes
    0.09
    xic
    0.09
    heets
    0.08
    æĺ¯æ²¡æľī
    0.08
    Little
    0.08
    çª
    0.08
    åIJĪèĤ¥å¸Ĥ
    0.08
    cv
    0.08
    kre
    0.08
    Activations Density 0.007%

    No Known Activations