© 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. 112822
    Prev
    Next
    INDEX
    Explanations

    activities involving "-ing" verbs

    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
    ingly
    -0.10
    ingu
    -0.09
    zers
    -0.09
     Schn
    -0.09
    -up
    -0.08
    nek
    -0.08
    ullah
    -0.08
    ANCE
    -0.08
    igkeit
    -0.08
     Grand
    -0.08
    POSITIVE LOGITS
     habits
    0.16
     spree
    0.16
     aids
    0.12
    hab
    0.12
     disorders
    0.11
     aid
    0.11
     disorder
    0.11
     utens
    0.11
    aid
    0.10
    åĻ¨
    0.10
    Activations Density 0.156%

    No Known Activations