© 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. 90959
    Prev
    Next
    INDEX
    Explanations

    danger and problems from illness, attack, or misfortune

    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
     wholesale
    -0.11
     egreg
    -0.09
     basically
    -0.09
    arend
    -0.08
     yay
    -0.08
     enthusiastically
    -0.08
    atu
    -0.08
     essentially
    -0.08
     entrenched
    -0.08
     staffing
    -0.08
    POSITIVE LOGITS
     consequences
    0.13
     anyhow
    0.12
     someday
    0.12
     threaten
    0.11
     Unexpected
    0.11
     unbearable
    0.11
     unexpected
    0.11
     unfore
    0.11
     abrupt
    0.11
     consequence
    0.10
    Activations Density 0.426%

    No Known Activations