© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    a good/lot/chance/art/way

    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
    erp
    -0.10
    urch
    -0.09
     excuses
    -0.09
     Eig
    -0.09
     Ein
    -0.09
     по
    -0.08
     outing
    -0.08
    isan
    -0.08
    itta
    -0.08
    elic
    -0.08
    POSITIVE LOGITS
     possibility
    0.16
     tendency
    0.16
     limit
    0.15
     chance
    0.15
     lot
    0.15
     reason
    0.15
     difference
    0.15
     shortage
    0.14
     saying
    0.14
     caveat
    0.13
    Activations Density 0.111%

    No Known Activations