© 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. 56968
    Prev
    Next
    INDEX
    Explanations

    forms of dominate

    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
    eners
    -0.10
    ä»ĸèĩªå·±
    -0.08
    emble
    -0.08
    èĢģåĮĸ
    -0.08
    ÑĥÑĩ
    -0.08
    bez
    -0.08
    åĿŀ
    -0.08
    çīĮåŃIJ
    -0.08
    moz
    -0.08
    .ft
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.12
    ously
    0.11
    çIJ¼
    0.10
    纷
    0.09
    æķ´ä¸ªäºº
    0.09
    cy
    0.09
    å±ĢéĿ¢
    0.09
     headlines
    0.09
    ä¸įäºĨ
    0.09
    ä¸ĢåĪĩ
    0.09
    Activations Density 0.017%

    No Known Activations