© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46732
    Prev
    Next
    INDEX
    Explanations

    suffix: "-al", "-ous", "-ic", "-ar"

    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
     thereof
    -0.09
    mons
    -0.08
    /part
    -0.08
    after
    -0.08
     Exclusive
    -0.08
     Sr
    -0.08
     monopoly
    -0.08
     devoted
    -0.08
     entirely
    -0.08
    929
    -0.08
    POSITIVE LOGITS
     Unary
    0.09
     pelvic
    0.09
     hel
    0.09
    .plist
    0.09
    egal
    0.09
     Rifle
    0.09
     accessor
    0.09
    [sizeof
    0.09
     hike
    0.09
    '+↵
    0.09
    Activations Density 0.017%

    No Known Activations