© 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. 89823
    Prev
    Next
    INDEX
    Explanations

    expressing positive sentiment

    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
     Civilization
    -0.11
     sed
    -0.11
     Enlight
    -0.10
     arous
    -0.10
     pne
    -0.10
     pity
    -0.10
     Webcam
    -0.10
     appealing
    -0.10
    oret
    -0.10
     solicit
    -0.10
    POSITIVE LOGITS
     incredible
    0.14
     positivity
    0.14
     collaborations
    0.14
     vib
    0.12
     dope
    0.12
     friendships
    0.12
     âĿ¤
    0.12
     pinch
    0.12
     gratitude
    0.11
     collaborative
    0.11
    Activations Density 0.777%

    No Known Activations