© 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. 34498
    Prev
    Next
    INDEX
    Explanations

    inquiry accepted/replied

    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
    åį´åıĪ
    -0.10
    çºłéĶĻ
    -0.09
    urat
    -0.09
    коÑģ
    -0.08
    çĴĢçĴ¨
    -0.08
    æĪĸå¤ļ
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    á¹£
    -0.08
    нÑĥÑĤ
    -0.08
    ilst
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.10
    eman
    0.09
    æľ¬çĿĢ
    0.09
    çĬ¬
    0.08
    landers
    0.08
    .nlm
    0.08
    _SOL
    0.08
    olem
    0.08
    æļ´
    0.08
    å¼ĢæĿ¥
    0.08
    Activations Density 0.049%

    No Known Activations