© 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. 33763
    Prev
    Next
    INDEX
    Explanations

    upcoming events and releases

    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
     ongoing
    -0.11
     recent
    -0.11
    ona
    -0.09
    vell
    -0.09
     current
    -0.09
     beginnings
    -0.09
    \(
    -0.08
    chi
    -0.08
     surprisingly
    -0.08
     upwards
    -0.08
    POSITIVE LOGITS
    /current
    0.17
     doom
    0.15
     deadlines
    0.12
    /prom
    0.12
     changes
    0.12
     generations
    0.11
     expiration
    0.11
    empt
    0.11
    ebin
    0.10
     paren
    0.10
    Activations Density 0.058%

    No Known Activations