© 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. 56490
    Prev
    Next
    INDEX
    Explanations

    acquiring or finding things

    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
    çŁ¥éģĵèĩªå·±
    -0.11
    infinity
    -0.10
    kart
    -0.09
    ä¾ĭè¡Į
    -0.09
     misd
    -0.09
    æĦŁåıĹ
    -0.08
    .toolbox
    -0.08
    .shtml
    -0.08
    IDA
    -0.08
     Proceed
    -0.08
    POSITIVE LOGITS
    äºīåıĸ
    0.16
     sources
    0.14
    æĿ¥æºIJ
    0.13
    sources
    0.13
     иÑģÑĤоÑĩник
    0.12
    Sources
    0.12
    å¸Ĥåľºä¸Ĭ
    0.12
     Sources
    0.12
    å¼ķè¿Ľ
    0.11
    èİ·åıĸ
    0.11
    Activations Density 0.084%

    No Known Activations