© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    theme announcement or theme ideas

    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
    ع
    -0.10
    iable
    -0.10
    deen
    -0.10
    mente
    -0.10
    ible
    -0.10
    man
    -0.09
    ÑĮ
    -0.08
    ÄĤ
    -0.08
    ¼
    -0.08
    ей
    -0.08
    POSITIVE LOGITS
    elves
    0.18
    perature
    0.12
    asurement
    0.12
    atics
    0.12
    åIJĦå¼Ĥ
    0.12
    kits
    0.11
    ATIC
    0.11
    atical
    0.11
    asured
    0.11
    ãģ£ãģįãĤĬ
    0.11
    Activations Density 0.019%

    No Known Activations