© 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. 31689
    Prev
    Next
    INDEX
    Explanations

    signals of distress or warning

    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
     readers
    -0.10
     Readers
    -0.09
    iac
    -0.09
    raq
    -0.09
     unnoticed
    -0.09
     Spar
    -0.09
     Ry
    -0.09
     BEN
    -0.09
     Dien
    -0.09
     Kurd
    -0.09
    POSITIVE LOGITS
     beware
    0.19
     Bew
    0.17
     indicative
    0.17
     suspicious
    0.15
     suspect
    0.15
     Indicates
    0.14
     indication
    0.14
     indications
    0.14
     distrust
    0.14
    indic
    0.13
    Activations Density 0.034%

    No Known Activations