© 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. 22907
    Prev
    Next
    INDEX
    Explanations

    problem solving asking for help

    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
    reu
    -0.08
    æĿª
    -0.08
    tol
    -0.08
    ç°ĩ
    -0.08
    uron
    -0.08
    æĶ¾è¿ĩ
    -0.08
    ä¸įå®Į
    -0.08
    ÙĬÙĦÙĬ
    -0.08
     Cater
    -0.08
    æĸ¤
    -0.08
    POSITIVE LOGITS
    对æѤ
    0.09
     assignable
    0.09
    ä¸Ģæ³¢
    0.09
    亨
    0.08
    vero
    0.08
     MU
    0.08
    让æ¶Īè´¹èĢħ
    0.08
    osos
    0.08
    å±ı
    0.08
    åIJ¬å¾Ĺ
    0.08
    Activations Density 0.509%

    No Known Activations