© 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. 6526
    Prev
    Next
    INDEX
    Explanations

    quoted sentence ending

    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
    ed
    -0.15
    ness
    -0.11
    UPI
    -0.10
    adam
    -0.10
    edBy
    -0.10
    eda
    -0.10
    ne
    -0.10
    ly
    -0.10
     Grip
    -0.10
    ssue
    -0.10
    POSITIVE LOGITS
     favour
    0.17
     emphas
    0.13
     humour
    0.12
     analys
    0.11
     neighbouring
    0.11
     analyse
    0.11
     harbour
    0.11
    hound
    0.11
     favoured
    0.11
     analysed
    0.11
    Activations Density 0.271%

    No Known Activations