© 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. 31232
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    /documents
    -0.11
    erval
    -0.11
    apan
    -0.10
    ogn
    -0.10
     '**
    -0.10
     Duc
    -0.10
    icap
    -0.10
     confusion
    -0.10
     Wis
    -0.10
     Winn
    -0.10
    POSITIVE LOGITS
     Cha
    0.09
     Fut
    0.08
     deterrent
    0.08
     eg
    0.08
    ron
    0.07
    ason
    0.07
     ie
    0.07
     pathetic
    0.07
    ivo
    0.07
    č
    0.07
    Activations Density 0.399%

    No Known Activations