© 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. 89996
    Prev
    Next
    INDEX
    Explanations

    Fidan, Gasimova, Farghana, Ethiopia, Afar

    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
    apel
    -0.12
     Uncategorized
    -0.10
     andre
    -0.10
    .FileReader
    -0.10
     doub
    -0.09
     handheld
    -0.09
    anal
    -0.09
    arel
    -0.09
    abal
    -0.09
     filmer
    -0.09
    POSITIVE LOGITS
    ystick
    0.09
    Alternate
    0.09
     Burst
    0.09
     AS
    0.09
    ristol
    0.09
    cro
    0.09
    zyst
    0.09
     prolifer
    0.09
     Cro
    0.09
    _AS
    0.09
    Activations Density 0.112%

    No Known Activations