© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    intended, LICENSE, Fast, -dependent, August

    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
    reas
    -0.09
    unes
    -0.09
     Bak
    -0.09
    ardi
    -0.08
     openly
    -0.08
     marc
    -0.08
    ocos
    -0.08
     envelope
    -0.08
    ières
    -0.08
     Barker
    -0.08
    POSITIVE LOGITS
    yen
    0.10
    lest
    0.09
    oyo
    0.09
     ape
    0.09
     steward
    0.09
     Curt
    0.09
    Dependency
    0.09
     fray
    0.08
     rookie
    0.08
    cour
    0.08
    Activations Density 0.001%

    No Known Activations