© 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. 31561
    Prev
    Next
    INDEX
    Explanations

    entity separators

    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
     Porto
    -0.08
     Owens
    -0.08
     fond
    -0.07
    (compact
    -0.07
     Moran
    -0.07
    ecom
    -0.07
    amate
    -0.07
    aint
    -0.07
     Leslie
    -0.07
     ãĥ»
    -0.07
    POSITIVE LOGITS
     ).↵↵
    0.13
     Lastly
    0.12
    achi
    0.11
    —all
    0.11
    ).↵↵
    0.11
    <|endoftext|>
    0.11
    ).</
    0.11
    .↵↵
    0.11
     plus
    0.11
     Finally
    0.10
    Activations Density 0.475%

    No Known Activations