© 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. 48685
    Prev
    Next
    INDEX
    Explanations

    descriptive positive adjectives

    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
    ogan
    -0.12
     Farr
    -0.10
     kenn
    -0.10
     Mug
    -0.10
     gimm
    -0.10
    cks
    -0.10
     follower
    -0.09
    emie
    -0.09
    aga
    -0.09
     hur
    -0.09
    POSITIVE LOGITS
     sight
    0.11
     standing
    0.10
     beyond
    0.10
     truly
    0.09
     Lair
    0.09
     sitting
    0.08
    ereal
    0.08
     enough
    0.08
     carving
    0.08
    ingly
    0.08
    Activations Density 0.025%

    No Known Activations