© 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. 48814
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or result

    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
     Hust
    -0.09
    dess
    -0.08
    å½ķ
    -0.08
    (Me
    -0.08
     indeed
    -0.08
     Faul
    -0.08
     CG
    -0.08
    inder
    -0.08
     troll
    -0.08
     Benefit
    -0.08
    POSITIVE LOGITS
    able
    0.13
    iddy
    0.11
    zig
    0.11
    pii
    0.11
    acci
    0.11
    /animate
    0.10
    tracking
    0.10
    /sw
    0.10
    abil
    0.10
    /connect
    0.10
    Activations Density 0.155%

    No Known Activations