© 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. 34793
    Prev
    Next
    INDEX
    Explanations

    .com or .org URLs

    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
    ç®Ģ称
    -0.10
    çĩ®
    -0.10
    ä¸ĵåijĺ
    -0.08
    æĸ°äº¬æĬ¥
    -0.08
    è¿ĺ好
    -0.08
    åħ±äº«åįķ车
    -0.08
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    è¿ĺåľ¨
    -0.08
    spath
    -0.08
    é¦Ļåij³
    -0.08
    POSITIVE LOGITS
    linger
    0.10
    .QueryString
    0.08
     Nev
    0.08
    steen
    0.08
     inc
    0.08
     occult
    0.08
    èĭĽ
    0.08
    å©Ĩ
    0.08
    auce
    0.08
    æ·±åĪ»çļĦ
    0.08
    Activations Density 0.099%

    No Known Activations