© 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. 49892
    Prev
    Next
    INDEX
    Explanations

    expressions regarding emotion

    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
    jem
    -0.12
     unintention
    -0.09
    oba
    -0.09
     invis
    -0.09
    .Once
    -0.09
     secretly
    -0.09
     STRICT
    -0.08
     remembered
    -0.08
    icl
    -0.08
     inadvertently
    -0.08
    POSITIVE LOGITS
     smiled
    0.18
     laughed
    0.18
     smile
    0.18
     chuckled
    0.17
     smiles
    0.16
     laugh
    0.16
     Laugh
    0.16
     laughs
    0.15
     frowned
    0.15
     smirk
    0.14
    Activations Density 0.018%

    No Known Activations