© 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. 90029
    Prev
    Next
    INDEX
    Explanations

    tip followed by of or colon

    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
     undercut
    -0.09
     signin
    -0.09
    ev
    -0.09
    gro
    -0.09
    ص
    -0.09
     litt
    -0.09
    WO
    -0.08
    IPHER
    -0.08
    eur
    -0.08
    ign
    -0.08
    POSITIVE LOGITS
    -tip
    0.14
    pling
    0.13
    pler
    0.13
    pee
    0.12
     iceberg
    0.12
    plers
    0.11
    pees
    0.11
    per
    0.11
    ografia
    0.11
    sters
    0.11
    Activations Density 0.034%

    No Known Activations