© 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. 48503
    Prev
    Next
    INDEX
    Explanations

    with emotions or reactions

    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
     quantity
    -0.11
    sit
    -0.11
    WS
    -0.10
    abr
    -0.10
     Saying
    -0.10
     saying
    -0.10
     posture
    -0.09
     demeanor
    -0.09
    lav
    -0.09
    eses
    -0.09
    POSITIVE LOGITS
     dismay
    0.19
     delight
    0.17
     regret
    0.16
     surprise
    0.16
     horror
    0.15
     pleasure
    0.14
     rue
    0.13
     alarm
    0.13
     aston
    0.13
     amusement
    0.13
    Activations Density 0.040%

    No Known Activations