© 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. 88380
    Prev
    Next
    INDEX
    Explanations

    investigating, was looking

    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
    apan
    -0.12
     prom
    -0.11
    arih
    -0.11
     Pierce
    -0.11
    ÑģÑĤан
    -0.10
    trail
    -0.10
    ibo
    -0.10
    afc
    -0.10
     bunk
    -0.10
     incor
    -0.10
    POSITIVE LOGITS
     smugg
    0.10
     heated
    0.08
    .exchange
    0.07
     Gee
    0.07
     mysteries
    0.07
     toe
    0.07
     forty
    0.07
     Composer
    0.07
     Helper
    0.07
     Bee
    0.07
    Activations Density 0.001%

    No Known Activations