© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    feelings 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
     presumably
    -0.16
     evidently
    -0.10
     supposedly
    -0.10
     apparently
    -0.10
    FUN
    -0.10
    laughter
    -0.09
     Appe
    -0.09
    aty
    -0.09
     relentlessly
    -0.09
     allegedly
    -0.09
    POSITIVE LOGITS
     hoping
    0.26
     wondering
    0.24
     feeling
    0.24
     wanting
    0.22
     afraid
    0.20
     unsure
    0.20
     glad
    0.19
     aware
    0.19
     knowing
    0.18
     thinking
    0.18
    Activations Density 0.041%

    No Known Activations