© 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. 91375
    Prev
    Next
    INDEX
    Explanations

    suspicion or diagnosis

    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
     Bair
    -0.10
    cie
    -0.08
     habit
    -0.07
    oir
    -0.07
    jer
    -0.07
     reciprocal
    -0.07
     Buf
    -0.07
    zens
    -0.07
     Shir
    -0.07
     logic
    -0.07
    POSITIVE LOGITS
     suspicions
    0.35
     suspicion
    0.31
     suspects
    0.26
     suspect
    0.26
     suspected
    0.26
     suspicious
    0.25
     Susp
    0.23
     hints
    0.19
     Sus
    0.19
     hint
    0.18
    Activations Density 0.083%

    No Known Activations