© 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. 27818
    Prev
    Next
    INDEX
    Explanations

    dates and timing

    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
     deadlines
    -0.14
     deadline
    -0.13
     Deadline
    -0.12
    Deadline
    -0.10
    appable
    -0.10
    æĺ¯éĿŀ
    -0.09
    aph
    -0.09
    izzy
    -0.09
     steep
    -0.09
    强迫
    -0.09
    POSITIVE LOGITS
    è·ĭ
    0.09
    ĶåĽŀ
    0.09
    unted
    0.09
    ä¸Ģ身
    0.08
    [string
    0.08
    iero
    0.08
    交ä»ĺ
    0.08
    -muted
    0.08
    è½
    0.08
    æľĽ
    0.08
    Activations Density 0.049%

    No Known Activations