© 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. 14879
    Prev
    Next
    INDEX
    Explanations

    thinking, guessing, expecting

    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
     Ful
    -0.11
     cl
    -0.09
     Wa
    -0.09
     Fuller
    -0.09
     Toro
    -0.09
     Promise
    -0.09
     Renew
    -0.09
    .ci
    -0.09
    Promise
    -0.09
     wa
    -0.09
    POSITIVE LOGITS
     thought
    0.26
     Thought
    0.26
    thought
    0.20
    Thought
    0.19
     suspected
    0.17
     figured
    0.16
     feared
    0.14
     guessed
    0.13
     expected
    0.13
     Didn
    0.13
    Activations Density 0.049%

    No Known Activations