© 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. 32245
    Prev
    Next
    INDEX
    Explanations

    specialized technical nouns

    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
     upt
    -0.09
     theirs
    -0.09
     hoops
    -0.08
    Nice
    -0.08
    mo
    -0.08
    rief
    -0.08
    undy
    -0.08
     mounts
    -0.08
    _mo
    -0.08
     Uncle
    -0.08
    POSITIVE LOGITS
     mlx
    0.11
     Venture
    0.10
    astos
    0.10
    .toolbox
    0.10
     pour
    0.09
    anten
    0.09
    Ùī
    0.09
    oire
    0.09
     margin
    0.09
     coloured
    0.09
    Activations Density 0.002%

    No Known Activations