© 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. 26024
    Prev
    Next
    INDEX
    Explanations

    Gustavo, Gust, Gus, Guthrie

    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
    bul
    -0.10
    idot
    -0.10
    onta
    -0.10
     quota
    -0.09
    âĻ¥
    -0.09
     bul
    -0.09
    etical
    -0.09
    zan
    -0.09
     discre
    -0.09
     Compound
    -0.09
    POSITIVE LOGITS
    atory
    0.15
    ATORY
    0.12
    afs
    0.10
     wind
    0.10
     gust
    0.10
    ing
    0.10
    erson
    0.09
    ary
    0.09
    avo
    0.09
    enburg
    0.09
    Activations Density 0.004%

    No Known Activations