© 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. 28759
    Prev
    Next
    INDEX
    Explanations

    settings and preferences

    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
    olo
    -0.09
     usernames
    -0.08
     automatically
    -0.08
     kepada
    -0.08
     names
    -0.08
    ^n
    -0.08
    onde
    -0.07
    kan
    -0.07
     thumbnails
    -0.07
     Bradley
    -0.07
    POSITIVE LOGITS
     Settings
    0.23
    SETTINGS
    0.22
     settings
    0.21
     Preferences
    0.21
     preferences
    0.21
     SETTINGS
    0.20
    Settings
    0.20
    _settings
    0.19
    Preferences
    0.18
    settings
    0.17
    Activations Density 1.138%

    No Known Activations