© 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. 22725
    Prev
    Next
    INDEX
    Explanations

    simulation and environment

    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
    UTOR
    -0.11
    ä¸įä¿¡
    -0.11
    line
    -0.09
    èİ«åIJį
    -0.09
    lessness
    -0.09
    .sb
    -0.09
    iest
    -0.09
    cheid
    -0.09
    flix
    -0.09
    usch
    -0.09
    POSITIVE LOGITS
    orgh
    0.10
    ously
    0.10
    rador
    0.10
     кÑĢови
    0.09
    æ³ķåºŃ
    0.09
    åĻ¨
    0.09
    ç¾İ好çĶŁæ´»
    0.09
    IAN
    0.09
    zed
    0.09
    äºĨå¤ļå°ij
    0.09
    Activations Density 0.036%

    No Known Activations