© 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. 49429
    Prev
    Next
    INDEX
    Explanations

    task and related concepts

    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
    ovel
    -0.11
    iable
    -0.11
    ÑģÑĮ
    -0.09
    rame
    -0.09
    QUI
    -0.09
    gie
    -0.09
     возможноÑģÑĤÑĮ
    -0.08
    thing
    -0.08
    æĸ¯é¡¿
    -0.08
    est
    -0.08
    POSITIVE LOGITS
    onomy
    0.12
    .FromResult
    0.11
    bar
    0.10
    èī°å·¨
    0.10
     Nunes
    0.10
    onaut
    0.09
    stell
    0.09
    /response
    0.09
    cla
    0.09
    sts
    0.09
    Activations Density 0.038%

    No Known Activations