© 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. 54804
    Prev
    Next
    INDEX
    Explanations

    core facility resources provided

    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
    ghi
    -0.09
     trò
    -0.09
    个åĪ«
    -0.09
    (KP
    -0.09
    eks
    -0.09
    ahi
    -0.09
    ç³Ĭ
    -0.08
    ä¸įç»ıæĦı
    -0.08
    è¾ľ
    -0.08
    _ASM
    -0.08
    POSITIVE LOGITS
    设æĸ½
    0.09
    adan
    0.09
     facility
    0.09
    machine
    0.09
     machine
    0.09
     Mut
    0.09
    æľºåĻ¨
    0.09
    _handles
    0.09
    æ©Ł
    0.09
    对å¤ĸå¼ĢæĶ¾
    0.08
    Activations Density 0.125%

    No Known Activations