© 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. 113518
    Prev
    Next
    INDEX
    Explanations

    medical or psychological symptoms

    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
     Neuroscience
    -0.10
     hormones
    -0.10
    IRA
    -0.10
     dotted
    -0.10
     Guild
    -0.10
     Kad
    -0.09
     heals
    -0.09
     neuroscience
    -0.09
    ERA
    -0.09
     prec
    -0.09
    POSITIVE LOGITS
     communications
    0.11
     reassuring
    0.10
     inexperienced
    0.10
     sitting
    0.10
     Communications
    0.09
     Sitting
    0.09
     paranoid
    0.09
     frightened
    0.09
     resting
    0.09
     Slate
    0.09
    Activations Density 0.113%

    No Known Activations