© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16586
    Prev
    Next
    INDEX
    Explanations

    asking what people think

    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
     adb
    -0.10
    Presence
    -0.10
    profil
    -0.10
    uelle
    -0.10
    HEME
    -0.10
     forwards
    -0.10
     helf
    -0.10
    IGN
    -0.10
    itivity
    -0.10
     Yates
    -0.10
    POSITIVE LOGITS
     thoughts
    0.27
     opinions
    0.22
     opinion
    0.22
     Thoughts
    0.22
     thought
    0.21
     thinks
    0.21
     think
    0.21
     thinking
    0.21
    thought
    0.21
     beliefs
    0.18
    Activations Density 0.195%

    No Known Activations