© 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. 3401
    Prev
    Next
    INDEX
    Explanations

    Indian surnames

    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
    Draft
    -0.11
    leen
    -0.09
    大èĩ´
    -0.09
    _draft
    -0.09
     decom
    -0.09
     trib
    -0.09
    DJ
    -0.08
     Draft
    -0.08
     Drew
    -0.08
    对æѤ
    -0.08
    POSITIVE LOGITS
    åľ¨åĮĹ京
    0.10
    issance
    0.09
    åĮĹ京
    0.09
    å¼¼
    0.08
    åįĬå¤ľ
    0.08
    çİĭåºľ
    0.08
    åĮĹ京åĨ¬å¥¥
    0.08
    ÑĪка
    0.08
    wit
    0.08
    igation
    0.08
    Activations Density 0.121%

    No Known Activations