© 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. 27537
    Prev
    Next
    INDEX
    Explanations

    war, battle, match, trial, operation, rally

    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
    èı
    -0.09
     summers
    -0.09
     colonies
    -0.09
    wend
    -0.09
     Kot
    -0.09
     convers
    -0.08
     fundra
    -0.08
     breathable
    -0.08
     Bren
    -0.08
    Ĭ¶
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁ
    0.12
     rocking
    0.11
     lasted
    0.11
     lasting
    0.10
     fier
    0.10
    ods
    0.10
     climax
    0.10
     concluded
    0.10
     between
    0.10
     themed
    0.10
    Activations Density 0.024%

    No Known Activations