© 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. 49705
    Prev
    Next
    INDEX
    Explanations

    host, MSC, violate, Page, What

    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
     Scrap
    -0.11
     wield
    -0.11
    uso
    -0.11
    mbH
    -0.11
     Porno
    -0.10
     Wilhelm
    -0.10
    /Branch
    -0.10
    acam
    -0.10
    kart
    -0.10
     esl
    -0.10
    POSITIVE LOGITS
    fed
    0.08
     attractive
    0.08
     peg
    0.08
    NETWORK
    0.08
    _places
    0.07
     fer
    0.07
     busy
    0.07
     hunt
    0.07
     Philosophy
    0.07
     Podcast
    0.07
    Activations Density 0.001%

    No Known Activations