© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    Guinea or Gu followed by capitalized names

    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
    ToFit
    -0.09
    ĴĮ
    -0.09
    ored
    -0.09
    alian
    -0.09
    ston
    -0.09
    lar
    -0.08
    asser
    -0.08
    CLS
    -0.08
    ed
    -0.08
    uel
    -0.08
    POSITIVE LOGITS
     Dillon
    0.11
    anine
    0.11
    illian
    0.10
    ummer
    0.10
    loe
    0.10
     overwhelmingly
    0.10
    anio
    0.10
     provid
    0.09
     odd
    0.09
    åı·
    0.09
    Activations Density 0.034%

    No Known Activations