© 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. 17529
    Prev
    Next
    INDEX
    Explanations

    duration of time

    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
    èĬ
    -0.11
    æ©¡
    -0.10
    eus
    -0.09
    伸æīĭ
    -0.09
    çĤ¸
    -0.08
    大è¡Ĺ
    -0.08
    æݬ
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    è¸ħ
    -0.08
    arma
    -0.08
    POSITIVE LOGITS
    å¤ļå¹´
    0.16
    _years
    0.14
     Years
    0.14
     mãi
    0.14
    æ°¸è¿ľ
    0.14
    åĩłåįģå¹´
    0.14
     years
    0.13
    Years
    0.13
     decades
    0.13
    åľ¨æľªæĿ¥
    0.13
    Activations Density 0.038%

    No Known Activations