© 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. 25960
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Crom
    -0.12
     allot
    -0.11
    AffineTransform
    -0.10
    rece
    -0.10
    hurst
    -0.10
     Magnus
    -0.10
     ging
    -0.10
    estro
    -0.10
     kron
    -0.10
     Tess
    -0.10
    POSITIVE LOGITS
     Stall
    0.08
     Carla
    0.08
     pij
    0.07
     Easter
    0.07
     Doll
    0.07
    ToDate
    0.07
     Ivory
    0.07
    voy
    0.07
     Martha
    0.07
     tb
    0.07
    Activations Density 1.851%

    No Known Activations