© 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. 10790
    Prev
    Next
    INDEX
    Explanations

    statistical applications and methods

    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
    骥
    -0.10
    å¼Ĥåľ°
    -0.10
    ever
    -0.09
     Shields
    -0.09
    bere
    -0.08
     determin
    -0.08
    åīĬ
    -0.08
    幸
    -0.08
    lä
    -0.08
    çŁ³å¤´
    -0.08
    POSITIVE LOGITS
    ç»Łè®¡
    0.14
    eln
    0.12
    /stat
    0.12
    .Stat
    0.12
    ç»Łè®¡æķ°æį®
    0.11
     statistical
    0.10
    è¿ľæĻ¯
    0.10
    äºŃ
    0.10
    æĪ·åı£
    0.10
    istical
    0.10
    Activations Density 0.098%

    No Known Activations