© 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. 62387
    Prev
    Next
    INDEX
    Explanations

    reported, officer, readers, multiple, xml

    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
    æĬĢå¸Ī
    -0.10
    ä¸įæĪIJ
    -0.10
    icit
    -0.09
    æijĨåľ¨
    -0.09
    /testing
    -0.09
    بخ
    -0.09
    èĿ
    -0.09
    ismo
    -0.09
    åĸī
    -0.08
    ScreenWidth
    -0.08
    POSITIVE LOGITS
    追踪
    0.13
    è·Łè¿Ľ
    0.11
    è·Łè¸ª
    0.11
    夹
    0.11
    æĭ¦æĪª
    0.10
    追赶
    0.10
    追
    0.10
     tracking
    0.09
    tracking
    0.09
     Tracking
    0.09
    Activations Density 0.037%

    No Known Activations