© 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. 2376
    Prev
    Next
    INDEX
    Explanations

    match / matching

    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
    çĿĢæīĭ
    -0.11
    åĮħ袱
    -0.10
    æĺİçĻ½
    -0.10
    æ¶ī足
    -0.10
    /github
    -0.10
    æĸŁ
    -0.09
    Asked
    -0.09
    åĬ¨åĬĽ
    -0.09
    tant
    -0.09
    为ä¹ĭ
    -0.09
    POSITIVE LOGITS
    åĮ¹éħį
    0.16
    .Match
    0.14
     match
    0.14
    .match
    0.14
     Match
    0.13
    .matches
    0.13
     matches
    0.13
    -match
    0.12
     matching
    0.12
    (match
    0.12
    Activations Density 0.140%

    No Known Activations