© 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. 16439
    Prev
    Next
    INDEX
    Explanations

    icon names

    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
     dem
    -0.09
     Lambert
    -0.09
     Across
    -0.09
    immel
    -0.08
    -photo
    -0.08
     wallpaper
    -0.08
    yon
    -0.08
     dist
    -0.07
    atham
    -0.07
     Harlem
    -0.07
    POSITIVE LOGITS
     icon
    0.21
     Icon
    0.18
    .svg
    0.15
    Icon
    0.15
    icon
    0.15
    ico
    0.14
    minus
    0.14
    aticon
    0.14
     icons
    0.14
    -icon
    0.13
    Activations Density 0.340%

    No Known Activations