© 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. 114765
    Prev
    Next
    INDEX
    Explanations

    must followed by verb

    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
    yar
    -0.09
    bron
    -0.09
    ourg
    -0.09
    pio
    -0.09
    ILT
    -0.09
     Pri
    -0.08
    atively
    -0.08
     Mont
    -0.08
     CRT
    -0.08
    most
    -0.08
    POSITIVE LOGITS
    n
    0.23
    ered
    0.19
    afa
    0.17
    s
    0.16
    ache
    0.16
    -have
    0.15
    angs
    0.15
     be
    0.14
    ached
    0.14
    aches
    0.14
    Activations Density 0.039%

    No Known Activations