© 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. 30699
    Prev
    Next
    INDEX
    Explanations

    word variations and related phrases

    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
    usz
    -0.08
     continuity
    -0.07
    chor
    -0.07
    ins
    -0.07
    Knife
    -0.07
    iero
    -0.07
    opensource
    -0.07
    852
    -0.07
    atta
    -0.07
     ad
    -0.07
    POSITIVE LOGITS
    lessly
    0.14
    word
    0.12
     Word
    0.11
     Dou
    0.11
    awy
    0.11
    vice
    0.11
    processing
    0.11
    less
    0.11
    count
    0.11
     count
    0.11
    Activations Density 0.049%

    No Known Activations