© 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. 35042
    Prev
    Next
    INDEX
    Explanations

    to some degree/extent

    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
    /tty
    -0.10
    èı±
    -0.10
    uzu
    -0.10
    .microsoft
    -0.09
    opes
    -0.09
    ÙĪÙĬ
    -0.09
    _tt
    -0.09
    gles
    -0.08
    itte
    -0.08
    Ä°L
    -0.08
    POSITIVE LOGITS
    æŁIJç§įç¨ĭ度
    0.19
    ä¸Ģå®ļç¨ĭ度
    0.17
    å¾Ī大ç¨ĭ度
    0.14
    éĻIJ度
    0.13
    æĿ¥è¯´
    0.13
    æŁIJç§į
    0.12
    èĢĮè¨Ģ
    0.12
    ä¸Ģå®ļçļĦ
    0.11
     certain
    0.11
    ç¨ĭ度
    0.11
    Activations Density 0.057%

    No Known Activations