© 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. 89170
    Prev
    Next
    INDEX
    Explanations

    operated by or owned by

    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
     gal
    -0.12
     Blanco
    -0.11
    /stretch
    -0.11
     shed
    -0.10
    eye
    -0.10
    gro
    -0.10
     jub
    -0.10
     beforehand
    -0.10
     Gro
    -0.10
     Mey
    -0.10
    POSITIVE LOGITS
     controlled
    0.14
     entirely
    0.14
     operated
    0.14
     run
    0.13
     jointly
    0.12
     managed
    0.11
     Controlled
    0.10
     owned
    0.10
     privately
    0.10
    -run
    0.10
    Activations Density 0.148%

    No Known Activations