© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    visited times

    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
    æıIJèµ·
    -0.10
    awi
    -0.10
    etur
    -0.09
    itur
    -0.09
    ä¿IJ
    -0.09
    缨
    -0.09
    ä¸įæİĴéĻ¤
    -0.09
    åĬ©éķ¿
    -0.09
    丧
    -0.08
    æ¤IJ
    -0.08
    POSITIVE LOGITS
    è¶Ł
    0.08
    åŀĤ
    0.08
    ç¿»
    0.08
    è¡¡
    0.08
    æľªæĽ¾
    0.08
    åĽ¢
    0.08
    Dice
    0.08
    åIJĮè¡Į
    0.08
    allo
    0.08
     Beste
    0.08
    Activations Density 0.032%

    No Known Activations