© 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. 4283
    Prev
    Next
    INDEX
    Explanations

    realization was / terrible / thinking

    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
    ange
    -0.09
     response
    -0.09
     agricult
    -0.09
     responses
    -0.08
     locally
    -0.08
    DEX
    -0.07
     mistakes
    -0.07
     Bis
    -0.07
     ac
    -0.07
    akov
    -0.07
    POSITIVE LOGITS
     thoughts
    0.27
     Thoughts
    0.25
     thinking
    0.19
    Thought
    0.18
    æĢĿ
    0.18
    Thinking
    0.17
    thought
    0.17
     Thinking
    0.17
     thought
    0.17
    thinking
    0.16
    Activations Density 0.122%

    No Known Activations