© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ite' or 'ute'

    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
    ness
    -0.30
    name
    -0.25
    ses
    -0.25
    set
    -0.24
    ly
    -0.24
    re
    -0.22
    n
    -0.22
    ship
    -0.22
    so
    -0.22
    net
    -0.22
    POSITIVE LOGITS
    ffect
    0.21
    azÄĥ
    0.21
    iros
    0.20
    cki
    0.20
    Ìģ
    0.20
    ño
    0.19
    aux
    0.19
    urope
    0.18
    lectric
    0.18
    iro
    0.18
    Activations Density 3.128%

    No Known Activations