© 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. 114136
    Prev
    Next
    INDEX
    Explanations

    what makes you tick or recognize

    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
    inka
    -0.11
    zet
    -0.10
    ordes
    -0.10
    _Status
    -0.10
     altogether
    -0.09
     lại
    -0.09
    oka
    -0.09
    ering
    -0.09
    isel
    -0.09
     pits
    -0.09
    POSITIVE LOGITS
     tick
    0.11
     passionately
    0.09
     Lud
    0.09
     besides
    0.09
     ench
    0.09
     fastest
    0.09
     quickest
    0.09
     ticks
    0.09
     personally
    0.09
    /ca
    0.09
    Activations Density 0.028%

    No Known Activations