© 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. 7182
    Prev
    Next
    INDEX
    Explanations

    Guy Kawasaki

    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
     comps
    -0.11
    ordin
    -0.10
     Bever
    -0.09
    mek
    -0.09
    nap
    -0.09
    keit
    -0.09
    ample
    -0.09
    qi
    -0.08
    adow
    -0.08
    sk
    -0.08
    POSITIVE LOGITS
    brush
    0.13
     Kawasaki
    0.10
    enne
    0.10
    dish
    0.10
    yyyy
    0.09
    eres
    0.09
    ertype
    0.09
    onne
    0.09
    ennon
    0.08
    liner
    0.08
    Activations Density 0.031%

    No Known Activations