© 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. 48765
    Prev
    Next
    INDEX
    Explanations

    stage, stage play, stage name, stage actress

    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
    tings
    -0.13
    der
    -0.12
    oit
    -0.10
    adin
    -0.10
    linger
    -0.10
    ridge
    -0.10
    phin
    -0.10
    erate
    -0.10
    ptom
    -0.09
    ders
    -0.09
    POSITIVE LOGITS
    coach
    0.23
     fright
    0.17
    craft
    0.17
    .Stage
    0.17
    hands
    0.14
    /screen
    0.13
    gers
    0.12
    hand
    0.11
    .stage
    0.11
     stage
    0.11
    Activations Density 0.049%

    No Known Activations