© 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. 31406
    Prev
    Next
    INDEX
    Explanations

    citations, references, and bracketed text

    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
     Russo
    -0.11
     Camb
    -0.11
    achs
    -0.10
    chio
    -0.09
     tra
    -0.09
     guts
    -0.09
    cpp
    -0.09
     camb
    -0.09
     Aid
    -0.09
     migrations
    -0.08
    POSITIVE LOGITS
    isle
    0.10
    acos
    0.09
     incred
    0.09
     jumper
    0.09
     frivol
    0.09
    rgan
    0.08
     dello
    0.08
    :Any
    0.08
    anner
    0.08
    ensi
    0.08
    Activations Density 0.011%

    No Known Activations