© 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. 35516
    Prev
    Next
    INDEX
    Explanations

    starting words/phrases

    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
    hip
    -0.09
    ç°ª
    -0.08
    ocked
    -0.08
    utoff
    -0.08
     Booker
    -0.08
    æŨ
    -0.08
     DIM
    -0.08
    nist
    -0.08
    _LAYER
    -0.08
    astro
    -0.08
    POSITIVE LOGITS
    ters
    0.11
    åľ¨å¸Ĥåľºä¸Ĭ
    0.10
    yor
    0.10
    æİĤ
    0.10
    eners
    0.10
    åľ¨è·¯ä¸Ĭ
    0.10
    melon
    0.09
    åľ¨åºĬä¸Ĭ
    0.09
     Dodd
    0.09
    åľ¨åĽ½åĨħ
    0.09
    Activations Density 0.007%

    No Known Activations