© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    key players

    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
    è¿¥
    -0.10
    樽
    -0.10
    社群
    -0.09
    å»ĵ
    -0.09
    躬
    -0.09
    é¡¿
    -0.09
    éĻĽ
    -0.09
    æĴŀ
    -0.09
    宽æĿ¾
    -0.08
    pth
    -0.08
    POSITIVE LOGITS
    巨头
    0.12
    巨人
    0.11
    åıĤä¸İèĢħ
    0.10
    VENT
    0.10
     presence
    0.09
    éĢīæīĭ
    0.09
     stret
    0.09
    åıĤä¸İåĪ°
    0.09
    æĬ¼
    0.08
    袢
    0.08
    Activations Density 0.080%

    No Known Activations