© 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. 29847
    Prev
    Next
    INDEX
    Explanations

    word "one" followed by new

    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
    IGIN
    -0.11
     Neville
    -0.11
     ^^
    -0.09
     Womens
    -0.08
     [/
    -0.08
     Gian
    -0.08
     azt
    -0.08
     FUCK
    -0.08
     cunt
    -0.08
     ce
    -0.08
    POSITIVE LOGITS
    (er
    0.12
    Sharper
    0.12
     gotta
    0.12
     déjÃł
    0.11
     Peek
    0.11
    -ing
    0.10
    izzle
    0.10
    âĢ¦but
    0.10
     âīł
    0.10
    iero
    0.10
    Activations Density 0.291%

    No Known Activations