© 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. 117004
    Prev
    Next
    INDEX
    Explanations

    cognitive distortions or negative thoughts

    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
     Mutual
    -0.11
     mutual
    -0.10
     init
    -0.09
     communic
    -0.09
     Gesture
    -0.09
    _Init
    -0.09
     Jetzt
    -0.09
     ambassadors
    -0.09
     Ghost
    -0.09
     ordinal
    -0.09
    POSITIVE LOGITS
     beliefs
    0.27
     Thoughts
    0.23
     thoughts
    0.23
     belief
    0.18
    belief
    0.18
     negative
    0.17
    Thought
    0.17
     habitual
    0.16
     untrue
    0.16
     irrational
    0.16
    Activations Density 0.176%

    No Known Activations