© 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. 58949
    Prev
    Next
    INDEX
    Explanations

    you telling

    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
    æľīè¿ĩ
    -0.10
    ableObject
    -0.10
    MakeRange
    -0.09
    elivery
    -0.09
    дол
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.09
    æľīæľº
    -0.09
    æ¡´
    -0.09
     него
    -0.09
    posal
    -0.09
    POSITIVE LOGITS
     about
    0.10
     rằng
    0.08
    æĽ´å¤ļä¿¡æģ¯
    0.08
    HS
    0.08
    wards
    0.08
    0.08
    âݯ
    0.08
     otherwise
    0.07
    vest
    0.07
     Formation
    0.07
    Activations Density 0.029%

    No Known Activations