© 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. 28681
    Prev
    Next
    INDEX
    Explanations

    beginning or ending actions

    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
     fits
    -0.08
     refr
    -0.08
    ayah
    -0.08
     Spending
    -0.07
     Sent
    -0.07
     candid
    -0.07
     suf
    -0.07
    _reserved
    -0.07
    958
    -0.06
    Chan
    -0.06
    POSITIVE LOGITS
     begun
    0.35
     commenced
    0.35
     ended
    0.34
     begins
    0.34
     began
    0.33
     started
    0.32
     ends
    0.32
     begin
    0.30
     commence
    0.30
     continues
    0.30
    Activations Density 0.445%

    No Known Activations