© 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. 25659
    Prev
    Next
    INDEX
    Explanations

    investigation or criterion or estimation

    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
     sitting
    -0.13
     seated
    -0.12
     seating
    -0.11
     cigaret
    -0.11
     Sitting
    -0.11
     kneeling
    -0.11
     upstairs
    -0.11
     handheld
    -0.10
     midnight
    -0.10
     televised
    -0.10
    POSITIVE LOGITS
     superst
    0.13
     altru
    0.13
     novelty
    0.13
     fetish
    0.13
     nostalgia
    0.12
     synerg
    0.12
     sentimental
    0.12
     selfish
    0.12
     democrat
    0.12
     destabil
    0.12
    Activations Density 5.164%

    No Known Activations