© 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. 115971
    Prev
    Next
    INDEX
    Explanations

    sound an alarm or signal fire

    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
    yer
    -0.09
     congratulate
    -0.08
    aul
    -0.08
    adan
    -0.07
    ê²
    -0.07
    uling
    -0.07
     Checking
    -0.07
    rod
    -0.07
     Schwarz
    -0.07
     clearance
    -0.07
    POSITIVE LOGITS
     alarm
    0.32
     alert
    0.29
     alarms
    0.26
     alerted
    0.25
     alerts
    0.25
     scream
    0.24
     help
    0.24
     alarmed
    0.24
     summon
    0.24
    alarm
    0.24
    Activations Density 0.182%

    No Known Activations