© 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. 33480
    Prev
    Next
    INDEX
    Explanations

    words ending in ard

    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
    ihan
    -0.11
    nym
    -0.10
    anna
    -0.10
    kir
    -0.10
     Pel
    -0.10
     Vaccine
    -0.09
    -Col
    -0.09
     Hay
    -0.09
    isos
    -0.09
    es
    -0.09
    POSITIVE LOGITS
     sod
    0.10
     unb
    0.09
    ogg
    0.09
    coin
    0.09
    ugal
    0.09
    ipes
    0.08
    oard
    0.08
    Alternate
    0.08
     audio
    0.08
     squat
    0.08
    Activations Density 0.001%

    No Known Activations