© 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. 5501
    Prev
    Next
    INDEX
    Explanations

    cognitive behavioral disorder treatment

    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
     maturity
    -0.12
     fingerprints
    -0.09
     demonstr
    -0.09
     ethos
    -0.09
    gne
    -0.09
    oeff
    -0.09
     mesmer
    -0.09
     membr
    -0.09
    pirit
    -0.09
     Horton
    -0.08
    POSITIVE LOGITS
     triggers
    0.18
     triggering
    0.18
     trigger
    0.18
     feared
    0.17
     procrast
    0.16
     Trigger
    0.16
     situations
    0.16
     anxious
    0.16
     anxiety
    0.15
     triggered
    0.15
    Activations Density 0.277%

    No Known Activations