© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    cyrillic letter 'k'

    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
     Orchestra
    -0.10
    reu
    -0.10
     connexion
    -0.10
    ering
    -0.10
     energetic
    -0.10
    asin
    -0.10
    ért
    -0.10
    erten
    -0.10
    emann
    -0.10
     Methodist
    -0.10
    POSITIVE LOGITS
    aal
    0.10
    asan
    0.09
     McD
    0.09
    ucher
    0.08
    aqu
    0.08
    aque
    0.07
    aan
    0.07
    o
    0.07
     Ny
    0.07
     lying
    0.07
    Activations Density 0.009%

    No Known Activations