© 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. 48628
    Prev
    Next
    INDEX
    Explanations

    tag search and tagging

    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
    izia
    -0.10
    okie
    -0.09
    nage
    -0.09
    ä¸ĢåŃĹ
    -0.09
    .shell
    -0.09
    éĶģ
    -0.09
    模èĮĥ
    -0.08
    enci
    -0.08
    è°ĥåĬ¨
    -0.08
    .stdin
    -0.08
    POSITIVE LOGITS
    /tag
    0.13
    tag
    0.12
    (Tag
    0.11
     tag
    0.11
    æłĩçŃ¾
    0.10
     Tag
    0.10
     tags
    0.10
    (TAG
    0.09
    (tags
    0.09
     tagName
    0.09
    Activations Density 0.054%

    No Known Activations