© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53175
    Prev
    Next
    INDEX
    Explanations

    words starting with max

    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
    лаг
    -0.10
    å¾Īæ·±
    -0.09
    zech
    -0.09
    axed
    -0.09
    ราว
    -0.09
    bine
    -0.09
    足
    -0.08
    orton
    -0.08
    è·
    -0.08
    wish
    -0.08
    POSITIVE LOGITS
    IMUM
    0.19
    imizer
    0.17
    imal
    0.15
    imize
    0.15
    ima
    0.15
    mium
    0.14
    illary
    0.13
    imized
    0.13
    imo
    0.12
    imum
    0.12
    Activations Density 0.050%

    No Known Activations