© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
    _selector
    -0.09
     nop
    -0.09
    acial
    -0.09
    ate
    -0.09
     Schmidt
    -0.09
     Kot
    -0.09
     postal
    -0.09
    asin
    -0.09
    EP
    -0.09
     absentee
    -0.09
    POSITIVE LOGITS
     [:
    0.09
     lic
    0.09
    virt
    0.09
    bdb
    0.09
     Fantasy
    0.08
     Divider
    0.08
     ogl
    0.08
     clap
    0.08
     Cly
    0.08
    jec
    0.08
    Activations Density 0.340%

    No Known Activations