© 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. 16408
    Prev
    Next
    INDEX
    Explanations

    suspicions and responses

    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
    atz
    -0.09
     indirectly
    -0.09
     Welt
    -0.09
    arend
    -0.09
     surre
    -0.09
     strangers
    -0.08
     Licht
    -0.08
     dynamically
    -0.08
     const
    -0.08
    terr
    -0.08
    POSITIVE LOGITS
     fooled
    0.27
     responds
    0.17
     respond
    0.17
     responded
    0.16
     Respond
    0.15
     countered
    0.14
     suspicions
    0.14
     susceptible
    0.14
     suspicious
    0.14
    respond
    0.14
    Activations Density 0.110%

    No Known Activations