© 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. 23354
    Prev
    Next
    INDEX
    Explanations

    video timing or start

    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
    äºı
    -0.09
    鸳
    -0.09
    åı¯éĿłçļĦ
    -0.08
    slick
    -0.08
    ä¸įä¸ĭ
    -0.08
     luaL
    -0.08
    åĵ¥ä»¬
    -0.08
    ç¨Ķ
    -0.08
    çĿģ
    -0.08
    俯
    -0.08
    POSITIVE LOGITS
    è§Ĩé¢ij
    0.15
     video
    0.14
    video
    0.14
     videos
    0.13
     Video
    0.12
     vidéo
    0.12
    Video
    0.12
    _video
    0.12
    (video
    0.11
    å½±çīĩ
    0.11
    Activations Density 0.235%

    No Known Activations