© 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. 48922
    Prev
    Next
    INDEX
    Explanations

    enough new, feedback, information, trust

    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
    Stan
    -0.08
     Stan
    -0.08
    anel
    -0.08
    uma
    -0.08
    essa
    -0.07
    edin
    -0.07
     Obl
    -0.07
    more
    -0.07
    kb
    -0.07
    uru
    -0.07
    POSITIVE LOGITS
     jap
    0.12
     sufficiently
    0.12
    gli
    0.12
    ihn
    0.11
    contro
    0.11
    contre
    0.11
     Pey
    0.11
    IFn
    0.10
     Hubb
    0.10
    pais
    0.10
    Activations Density 0.034%

    No Known Activations