© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89240
    Prev
    Next
    INDEX
    Explanations

    Chittenden, Wittichenau, Wittenberg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     favoured
    -0.11
     thin
    -0.09
    pii
    -0.09
     Preferred
    -0.09
    iale
    -0.09
     favored
    -0.09
     sui
    -0.09
    ugin
    -0.09
    heit
    -0.09
     retrospective
    -0.09
    POSITIVE LOGITS
    sburgh
    0.14
    lename
    0.11
    engl
    0.10
    orio
    0.10
    aker
    0.10
    enden
    0.10
    enser
    0.09
    elm
    0.09
    Wer
    0.09
    ENTION
    0.09
    Activations Density 0.041%

    No Known Activations