© 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. 89291
    Prev
    Next
    INDEX
    Explanations

    route names, numbers, or descriptions

    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
    light
    -0.12
    ged
    -0.12
    ëĭ¤
    -0.11
    aye
    -0.10
    hoot
    -0.10
    mont
    -0.10
    yer
    -0.10
    hawk
    -0.10
    ivol
    -0.10
    holder
    -0.10
    POSITIVE LOGITS
    ledge
    0.16
    inely
    0.15
    (Route
    0.10
    (routes
    0.09
    inue
    0.09
    /network
    0.09
    abouts
    0.08
    (route
    0.08
    up
    0.08
    ches
    0.08
    Activations Density 0.064%

    No Known Activations