© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33396
    Prev
    Next
    INDEX
    Explanations

    severity of pain or illness

    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
     loosely
    -0.13
     shaken
    -0.12
     unwitting
    -0.12
     assim
    -0.11
     rested
    -0.10
     Shades
    -0.10
     boosts
    -0.10
    aji
    -0.10
     wound
    -0.10
    cls
    -0.10
    POSITIVE LOGITS
     intens
    0.20
     intense
    0.19
     intensified
    0.19
     unbearable
    0.18
     intensity
    0.18
     worse
    0.17
     intoler
    0.16
     wors
    0.16
     severe
    0.15
     severity
    0.14
    Activations Density 0.083%

    No Known Activations