© 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. 57297
    Prev
    Next
    INDEX
    Explanations

    healthy persons, children, adults

    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
    orro
    -0.10
    sen
    -0.09
    èĥľ
    -0.08
    åŀ®
    -0.08
    èĮĥ
    -0.08
    ä¸į说
    -0.08
    åĵĦ
    -0.08
    ãĥIJãĥ©
    -0.08
    ught
    -0.08
    ä¸įä¿¡
    -0.08
    POSITIVE LOGITS
    ÙĨÙĪ
    0.10
    çı©
    0.10
     Griffith
    0.09
    ated
    0.09
    书åºĹ
    0.08
    çıł
    0.08
    éĻ¤å¤ĸ
    0.08
     Hass
    0.08
    æ¸İ
    0.08
    æĬij
    0.08
    Activations Density 0.005%

    No Known Activations