© 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. 22705
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    ogs
    -0.09
    èĥľ
    -0.08
    æݺ
    -0.08
    CHAN
    -0.08
    reno
    -0.08
    Difficulty
    -0.08
    æħĭ
    -0.08
    .setTo
    -0.08
    hawk
    -0.08
    ater
    -0.08
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.12
    è¿Ļ个åIJįåŃĹ
    0.11
    åĪ°æĿ¥
    0.11
    åIJ¬åĪ°
    0.10
    æµģæ°´
    0.10
    è¿Ļ款游æĪı
    0.09
    æŀ¶åŃIJ
    0.09
    adir
    0.09
    è¿Ļè¯Ŀ
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    Activations Density 0.046%

    No Known Activations