© 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. 30907
    Prev
    Next
    INDEX
    Explanations

    stare, star, starring

    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
    nr
    -0.11
     genu
    -0.11
    Hide
    -0.11
    129
    -0.10
    steady
    -0.10
     Samar
    -0.10
     onTouch
    -0.10
     steady
    -0.10
     recourse
    -0.10
     Cutting
    -0.10
    POSITIVE LOGITS
     blank
    0.13
    blank
    0.10
     down
    0.10
    kest
    0.09
     bleak
    0.09
     dag
    0.09
    vation
    0.08
    ving
    0.08
    bucks
    0.08
     adam
    0.08
    Activations Density 0.021%

    No Known Activations