© 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. 10799
    Prev
    Next
    INDEX
    Explanations

    wondering and asking

    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
    ä½łçľĭ
    -0.10
    utz
    -0.09
    è¾İ
    -0.09
    毫ä¸įçĬ¹è±«
    -0.08
    èĩ³æĸ¼
    -0.08
    째
    -0.08
    ä¸Ģåıª
    -0.08
    iei
    -0.08
    ened
    -0.08
    ility
    -0.08
    POSITIVE LOGITS
    immel
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    ingly
    0.10
    lijke
    0.10
    ä¸įå·²
    0.10
    land
    0.10
    ously
    0.09
    ForResult
    0.09
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
    lust
    0.09
    Activations Density 0.013%

    No Known Activations