© 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. 62413
    Prev
    Next
    INDEX
    Explanations

    Smithsonian Institution, Pulitzer Prize, Library of Congress

    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
    aces
    -0.09
    wares
    -0.09
    icas
    -0.08
    orer
    -0.08
    æĢĽ
    -0.08
    mith
    -0.08
    oyer
    -0.08
    folio
    -0.08
    erman
    -0.08
    è¦ģçĤ¹
    -0.08
    POSITIVE LOGITS
    å·´å·´
    0.12
    ä¸įçķĻ
    0.10
    ä¸įå¿ħ
    0.10
    åĪĨå±Ģ
    0.09
    è§ī
    0.09
    ä¸įçĶ¨
    0.09
     Institution
    0.09
    esco
    0.09
    åķŃ
    0.09
    ogle
    0.09
    Activations Density 0.006%

    No Known Activations