© 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. 47801
    Prev
    Next
    INDEX
    Explanations

    technical components or devices

    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
     “
    -0.09
     practically
    -0.08
     favoured
    -0.08
     finely
    -0.08
     Cran
    -0.08
     ÂŃ
    -0.08
     ‘
    -0.07
    ...↵↵
    -0.07
     micro
    -0.07
     begr
    -0.07
    POSITIVE LOGITS
     Bou
    0.12
     osc
    0.12
     Wade
    0.12
    /Dk
    0.12
    uppercase
    0.11
     slogans
    0.11
     indeb
    0.11
    دÙĩ
    0.11
     toJSON
    0.11
    uba
    0.11
    Activations Density 0.002%

    No Known Activations