© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6719
    Prev
    Next
    INDEX
    Explanations

    presentation

    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
    éĻ¤éĿŀ
    -0.09
    çŁŃä¿¡
    -0.09
     znaj
    -0.09
    嵩
    -0.09
    quil
    -0.09
    ROW
    -0.09
    追
    -0.09
    湫
    -0.08
     вÑĭÑĢажен
    -0.08
    éĩįéĩijå±ŀ
    -0.08
    POSITIVE LOGITS
     presentation
    0.19
     presentations
    0.18
    presentation
    0.16
     Presentation
    0.16
    æ¼Ķ讲
    0.14
    Presentation
    0.13
    æ¼Ķ示
    0.13
     trình
    0.13
    ãĥĹãĥ¬ãĤ¼
    0.12
    resentation
    0.11
    Activations Density 0.045%

    No Known Activations