© 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. 32973
    Prev
    Next
    INDEX
    Explanations

    online and digital technologies

    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
    纪
    -0.09
    æĭĻ
    -0.09
    voy
    -0.09
    æ´ŀå¯Ł
    -0.08
    .pm
    -0.08
    ç´Ģ
    -0.08
    åľºéĿ¢
    -0.08
    (Default
    -0.08
    è¿°
    -0.08
    uple
    -0.08
    POSITIVE LOGITS
    äºij端
    0.10
    羡æħķ
    0.10
    æķ°åŃĹåĮĸ
    0.10
    麸
    0.10
    nev
    0.10
    åıĸ代
    0.09
    线ä¸Ĭ
    0.09
    нев
    0.09
    æ·ĺæ±°
    0.09
    tps
    0.08
    Activations Density 0.263%

    No Known Activations