© 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. 115834
    Prev
    Next
    INDEX
    Explanations

    Sudden interruption or appearance

    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
     segments
    -0.10
    lund
    -0.09
     Hudson
    -0.09
     segment
    -0.09
    pta
    -0.08
    airo
    -0.08
    egment
    -0.08
    antic
    -0.08
     immediately
    -0.08
    Brief
    -0.08
    POSITIVE LOGITS
     voice
    0.21
     sudden
    0.17
     voices
    0.16
     interruption
    0.16
     interrupts
    0.16
     footsteps
    0.16
    interrupt
    0.16
     suddenly
    0.15
     interrupt
    0.15
     movement
    0.15
    Activations Density 0.070%

    No Known Activations