© 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. 30830
    Prev
    Next
    INDEX
    Explanations

    and such

    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
    夹
    -0.10
    æħij
    -0.09
    æİIJ
    -0.09
    anni
    -0.09
    egin
    -0.08
    主åĬ¨æĢ§
    -0.08
    æıı
    -0.08
    绽
    -0.08
    æľīå¾Ī大
    -0.08
    ä¾®
    -0.08
    POSITIVE LOGITS
    æĽ´å¥½çļĦ
    0.09
    ements
    0.08
    ван
    0.08
    _strerror
    0.08
    LEE
    0.08
    룩
    0.08
    ائر
    0.08
    éĻĭ
    0.08
    æ°¨éħ¸
    0.08
    olini
    0.08
    Activations Density 0.073%

    No Known Activations