© 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. 116680
    Prev
    Next
    INDEX
    Explanations

    backstroke; north; belly; default; option

    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
     Wy
    -0.14
    icha
    -0.12
    Wy
    -0.12
    905
    -0.10
    iou
    -0.10
     clockwise
    -0.10
    appropri
    -0.10
     komple
    -0.10
     Personally
    -0.10
    clipboard
    -0.10
    POSITIVE LOGITS
    ores
    0.09
     Conrad
    0.08
     Mug
    0.08
     Catal
    0.08
     atop
    0.08
    aea
    0.08
     goof
    0.08
     mug
    0.08
     entitlement
    0.08
    gger
    0.07
    Activations Density 0.006%

    No Known Activations