© 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. 29853
    Prev
    Next
    INDEX
    Explanations

    crying

    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
    æĢĿæĥ³
    -0.09
    éĦ¯
    -0.09
    izo
    -0.08
    izz
    -0.08
    loom
    -0.08
    edException
    -0.08
    ฯ
    -0.08
    orns
    -0.08
    mente
    -0.08
    ibs
    -0.08
    POSITIVE LOGITS
    å¥ł
    0.11
    窿
    0.10
    ucid
    0.10
    峤
    0.09
    ä¸įåĩºæĿ¥
    0.09
    åĴĮåıijå±ķ
    0.09
    æĮ½åĽŀ
    0.09
    濯
    0.09
    беÑĢ
    0.09
    ogenic
    0.09
    Activations Density 0.007%

    No Known Activations