© 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. 115082
    Prev
    Next
    INDEX
    Explanations

    stop, halt, pause, cancel, cease

    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
     freeing
    -0.08
     Beard
    -0.08
     borrow
    -0.07
    sip
    -0.07
     dispos
    -0.07
     degradation
    -0.07
     occupied
    -0.07
    coon
    -0.07
    nv
    -0.07
     sne
    -0.07
    POSITIVE LOGITS
     stop
    0.54
     stopping
    0.52
     stopped
    0.52
     stops
    0.51
     halt
    0.49
     STOP
    0.48
     Stop
    0.47
    -stop
    0.45
     halted
    0.45
    åģľ
    0.45
    Activations Density 0.282%

    No Known Activations