© 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. 46743
    Prev
    Next
    INDEX
    Explanations

    STOP, interruption, minimize

    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
    aber
    -0.10
    hyper
    -0.09
    DIFF
    -0.09
     Pul
    -0.09
     falls
    -0.09
     spontaneous
    -0.09
     hyper
    -0.09
     canon
    -0.08
     rallying
    -0.08
     Fountain
    -0.08
    POSITIVE LOGITS
     STOP
    0.12
    alfa
    0.12
    -stop
    0.12
     interrupt
    0.12
     Stop
    0.12
     interruption
    0.11
     distracting
    0.11
     distraction
    0.11
     quel
    0.11
     Intercept
    0.11
    Activations Density 0.011%

    No Known Activations