© 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. 62199
    Prev
    Next
    INDEX
    Explanations

    science, flat-out, Bible, Matrix, Picasso

    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
    æ¸ħæ¾Ī
    -0.09
    大åħ¨
    -0.09
    trys
    -0.09
    antes
    -0.08
    _Abstract
    -0.08
    为主
    -0.08
    å£
    -0.08
    aims
    -0.08
    æµİ
    -0.08
    ган
    -0.08
    POSITIVE LOGITS
    éĺ´è°ĭ
    0.12
    论
    0.11
     conspiracy
    0.11
    伪
    0.10
    tdown
    0.09
    ç§ijåѦ
    0.09
    èľ¥
    0.09
    æļĩ
    0.09
    éĴ¦
    0.09
    åºĹéĩĮ
    0.09
    Activations Density 0.080%

    No Known Activations