© 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. 89148
    Prev
    Next
    INDEX
    Explanations

    you/you followed by punctuation or conjunctions

    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
     bef
    -0.11
     beloved
    -0.11
    typeid
    -0.10
    ...',↵
    -0.10
    evin
    -0.10
     heaven
    -0.10
     iam
    -0.09
    _hook
    -0.09
    rique
    -0.09
    acle
    -0.09
    POSITIVE LOGITS
     Seymour
    0.10
    yd
    0.09
    yte
    0.09
     too
    0.09
     bunch
    0.09
    ichen
    0.09
    aska
    0.08
     tremendously
    0.08
    inati
    0.08
     Super
    0.08
    Activations Density 0.014%

    No Known Activations