© 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. 90040
    Prev
    Next
    INDEX
    Explanations

    never followed by past participle

    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
    /OR
    -0.11
    wnd
    -0.10
    lor
    -0.10
     showers
    -0.10
     dilig
    -0.09
     sine
    -0.09
     originals
    -0.09
     grav
    -0.09
     stared
    -0.08
    /arm
    -0.08
    POSITIVE LOGITS
     knowingly
    0.12
     afterward
    0.11
     Perry
    0.10
    SEE
    0.10
     previously
    0.10
     yet
    0.09
     quite
    0.09
    FW
    0.09
     harb
    0.09
    aho
    0.09
    Activations Density 0.026%

    No Known Activations