© 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. 112241
    Prev
    Next
    INDEX
    Explanations

    emotions and states of mind

    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
     Hung
    -0.12
    het
    -0.11
    .ft
    -0.11
    ghi
    -0.10
    gies
    -0.10
    enda
    -0.10
     tys
    -0.10
    utan
    -0.10
     Bradford
    -0.10
    GBT
    -0.10
    POSITIVE LOGITS
     bile
    0.09
     wash
    0.09
    icha
    0.08
     aerobic
    0.08
     mixed
    0.08
     sadness
    0.08
     Vine
    0.08
    —who
    0.07
     -*
    0.07
     wondered
    0.07
    Activations Density 0.012%

    No Known Activations