© 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. 29751
    Prev
    Next
    INDEX
    Explanations

    The following noun

    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
     Coch
    -0.11
     Mei
    -0.10
     outing
    -0.10
    orry
    -0.10
    ork
    -0.10
     Cunningham
    -0.10
     stap
    -0.10
     joint
    -0.09
     uncon
    -0.09
     swo
    -0.09
    POSITIVE LOGITS
    rn
    0.10
     Rosenstein
    0.09
    atos
    0.09
     fraternity
    0.09
     ~~
    0.09
    atron
    0.09
    TED
    0.08
     quint
    0.08
     creds
    0.08
    rail
    0.08
    Activations Density 0.001%

    No Known Activations