© 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. 57498
    Prev
    Next
    INDEX
    Explanations

    few times/days/months/years

    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
    عÙĪا
    -0.10
    äºĽè®¸
    -0.09
    é£ŀæī¬
    -0.09
    æĶ¹ç¼ĸ
    -0.08
    MMM
    -0.08
    éĿŀ常å¤ļçļĦ
    -0.08
    ss
    -0.08
    .Lang
    -0.08
    èĭ¥å¹²
    -0.08
    MMMM
    -0.08
    POSITIVE LOGITS
     dozen
    0.15
    /all
    0.12
    ìĶ©
    0.10
    ÑĩиÑģлен
    0.10
    /../
    0.10
    place
    0.09
    teenth
    0.09
    odus
    0.09
     hundred
    0.09
     thousand
    0.09
    Activations Density 0.033%

    No Known Activations