© 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. 30615
    Prev
    Next
    INDEX
    Explanations

    action verbs in -ing

    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
     enough
    -0.09
    kker
    -0.09
     neatly
    -0.09
     Refugee
    -0.09
     halfway
    -0.09
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
    ivo
    -0.09
     occas
    -0.08
    legate
    -0.08
     Enough
    -0.08
    POSITIVE LOGITS
    zek
    0.12
    /debug
    0.12
     deciding
    0.11
     determining
    0.10
    awe
    0.10
    /search
    0.09
     Shea
    0.09
     Replies
    0.09
     decide
    0.09
    åĪ«
    0.09
    Activations Density 0.462%

    No Known Activations