© 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. 30283
    Prev
    Next
    INDEX
    Explanations

    probability and chance

    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
     Dia
    -0.10
     opposite
    -0.09
     Ingram
    -0.09
    gart
    -0.09
    Untitled
    -0.09
    613
    -0.09
     Rowe
    -0.09
    ilos
    -0.08
    Assert
    -0.08
     Artist
    -0.08
    POSITIVE LOGITS
     favors
    0.12
     slim
    0.12
     anyone
    0.12
     stacked
    0.11
     anybody
    0.11
    fat
    0.10
     Canter
    0.10
     Fav
    0.10
     fav
    0.10
     favor
    0.09
    Activations Density 0.021%

    No Known Activations