© 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. 31780
    Prev
    Next
    INDEX
    Explanations

    around the world

    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
     hence
    -0.07
     somehow
    -0.07
     here
    -0.07
     gotta
    -0.07
     evid
    -0.07
    oder
    -0.07
     consequ
    -0.06
     rightfully
    -0.06
     strateg
    -0.06
    ...
    -0.06
    POSITIVE LOGITS
    (ph
    0.12
     boon
    0.12
    geries
    0.12
     CASCADE
    0.12
     Hartford
    0.12
    uptime
    0.12
    aze
    0.12
    erial
    0.12
    yre
    0.11
    AML
    0.11
    Activations Density 0.268%

    No Known Activations