© 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. 5305
    Prev
    Next
    INDEX
    Explanations

    user management

    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
    hip
    -0.12
    uml
    -0.09
    ORB
    -0.09
     ticker
    -0.09
    orb
    -0.09
    ED
    -0.09
    isti
    -0.09
    uits
    -0.08
     pad
    -0.08
    uit
    -0.08
    POSITIVE LOGITS
     manuals
    0.11
    manual
    0.11
    amen
    0.11
     Avatar
    0.10
     account
    0.10
    names
    0.10
    -agent
    0.10
     manual
    0.10
    -defined
    0.10
     avatar
    0.10
    Activations Density 0.064%

    No Known Activations