© 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. 38648
    Prev
    Next
    INDEX
    Explanations

    signing athletes and 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
    çij¶
    -0.10
    hare
    -0.10
    (sr
    -0.08
    closed
    -0.08
    åѤ
    -0.08
    çŁ³å®¶
    -0.08
    伤çĹħ
    -0.08
    stre
    -0.08
    unal
    -0.08
    NR
    -0.07
    POSITIVE LOGITS
    çĮ·
    0.09
    å°ıé¢Ŀ
    0.09
    èľľ
    0.09
    缤
    0.09
    ´Ī
    0.09
    çĽĺ
    0.09
     Hutchinson
    0.09
     narr
    0.08
    à¸łà¸²à¸§à¸°
    0.08
    åĵij
    0.08
    Activations Density 0.015%

    No Known Activations