© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31490
    Prev
    Next
    INDEX
    Explanations

    term definition or subsequent items

    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
    arily
    -0.09
    tings
    -0.09
    /print
    -0.09
    emaker
    -0.09
    auce
    -0.08
    erm
    -0.08
    arna
    -0.08
    bum
    -0.08
    urn
    -0.08
    aned
    -0.08
    POSITIVE LOGITS
    inals
    0.22
    perature
    0.20
    /ph
    0.12
    isle
    0.12
    olecular
    0.12
    antino
    0.12
    ament
    0.12
    ék
    0.11
    ios
    0.11
    ész
    0.11
    Activations Density 0.104%

    No Known Activations