© 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. 26946
    Prev
    Next
    INDEX
    Explanations

    Lancaster, Alexander, Cumberland

    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
    shed
    -0.13
    ï¸
    -0.11
    -même
    -0.10
    lez
    -0.10
    æļĩ
    -0.09
    èĽ¸
    -0.09
    ETYPE
    -0.09
    ä¼Ĭæĸ¯
    -0.09
    aded
    -0.09
    á»ĩ
    -0.09
    POSITIVE LOGITS
    alog
    0.11
    /OR
    0.10
    alm
    0.10
    /or
    0.09
    rim
    0.09
    åīįæıIJæĺ¯
    0.08
    oops
    0.08
    ุม
    0.08
    iggs
    0.08
    ģını
    0.08
    Activations Density 0.019%

    No Known Activations