© 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. 49437
    Prev
    Next
    INDEX
    Explanations

    Copyright holder information

    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
    .*(
    -0.11
    ↵↵↵↵↵↵↵↵↵↵
    -0.11
    zie
    -0.11
    Furthermore
    -0.11
    ....↵
    -0.11
    ]**
    -0.11
    ..↵↵
    -0.11
    dda
    -0.10
    However
    -0.10
    however
    -0.10
    POSITIVE LOGITS
    ORG
    0.14
    Us
    0.12
    Overview
    0.12
    Edge
    0.11
    Updated
    0.11
    interest
    0.11
    Em
    0.10
    Off
    0.10
    Bo
    0.10
    Industry
    0.10
    Activations Density 1.667%

    No Known Activations