© 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. 26190
    Prev
    Next
    INDEX
    Explanations

    bride/brid variations and associated words

    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
    ito
    -0.09
    ilda
    -0.08
    itr
    -0.08
    adia
    -0.08
    aya
    -0.08
    resco
    -0.07
    uld
    -0.07
    obi
    -0.07
    vy
    -0.07
     Griffin
    -0.07
    POSITIVE LOGITS
    maid
    0.17
    maids
    0.15
    zilla
    0.15
    gest
    0.13
     groom
    0.12
     maiden
    0.12
     limb
    0.12
    -to
    0.11
    gom
    0.11
    brid
    0.11
    Activations Density 0.009%

    No Known Activations