© 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. 91803
    Prev
    Next
    INDEX
    Explanations

    mood and mood-related states

    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
    yan
    -0.10
     throat
    -0.10
     bre
    -0.09
    codec
    -0.09
    eat
    -0.09
    ailed
    -0.09
    '
    -0.09
     humane
    -0.09
    peri
    -0.09
    aus
    -0.09
    POSITIVE LOGITS
     swings
    0.22
    iness
    0.14
    swing
    0.13
     swing
    0.12
     Swing
    0.11
     disorders
    0.11
     disorder
    0.11
     swinger
    0.10
     stabil
    0.10
     bipolar
    0.10
    Activations Density 0.010%

    No Known Activations