© 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. 62250
    Prev
    Next
    INDEX
    Explanations

    confused or puzzled state

    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
    oris
    -0.10
    æ±
    -0.09
    nist
    -0.08
     кÑĢови
    -0.08
     getDescription
    -0.08
     пÑĥнк
    -0.08
    åĶ¿
    -0.08
    umes
    -0.08
    osen
    -0.07
     exig
    -0.07
    POSITIVE LOGITS
    ingly
    0.14
    ä¸įæ¸ħ
    0.11
    eners
    0.10
    ä¸į解
    0.10
    erten
    0.10
    оÑģÑĤи
    0.10
    azz
    0.10
    ä¼Ĭæĭī
    0.10
    èµ°åľ¨
    0.10
     налиÑĩие
    0.09
    Activations Density 0.019%

    No Known Activations