© 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. 53891
    Prev
    Next
    INDEX
    Explanations

    (AP) —

    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
    appa
    -0.09
    bol
    -0.09
    дÑĢ
    -0.09
    çłĶ讨
    -0.09
    uper
    -0.08
    åĿ
    -0.08
    rg
    -0.08
    æīĢ以说
    -0.08
    åħīèį£
    -0.08
    çĥĽ
    -0.08
    POSITIVE LOGITS
    epy
    0.10
    ä¸ĢåĪĻ
    0.09
    erot
    0.09
    çīĮ
    0.09
    ldr
    0.09
     getenv
    0.09
    ewis
    0.09
    .Areas
    0.09
    USED
    0.09
    bens
    0.09
    Activations Density 0.026%

    No Known Activations