© 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. 27780
    Prev
    Next
    INDEX
    Explanations

    round of golf or tournament

    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
    lection
    -0.10
    -0.09
    pery
    -0.09
    --------------------------------------------------------------------------↵
    -0.09
    enz
    -0.09
    à¹Ħà¸ĭ
    -0.09
    çĵ£
    -0.09
    裳
    -0.09
    ../../../
    -0.09
     vòng
    -0.09
    POSITIVE LOGITS
    ings
    0.15
    edList
    0.13
    icals
    0.12
    abouts
    0.11
    edException
    0.11
    worm
    0.11
    ers
    0.11
    elay
    0.10
    ney
    0.10
    about
    0.10
    Activations Density 0.017%

    No Known Activations