© 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. 115146
    Prev
    Next
    INDEX
    Explanations

    `Test` then `Status` or `Route`

    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
     lining
    -0.10
    .tx
    -0.10
     mouth
    -0.10
    mouth
    -0.10
     accus
    -0.10
     handshake
    -0.10
     gaze
    -0.10
     muzzle
    -0.10
     sperma
    -0.10
     Eu
    -0.10
    POSITIVE LOGITS
     Tick
    0.18
     tick
    0.16
     scratch
    0.14
     gigg
    0.14
     scratching
    0.14
    Tick
    0.13
     TICK
    0.12
     Goose
    0.12
     mo
    0.12
     goose
    0.12
    Activations Density 0.067%

    No Known Activations