© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114723
    Prev
    Next
    INDEX
    Explanations

    magical word

    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
    ly
    -0.18
    est
    -0.14
    ess
    -0.10
    ist
    -0.09
    LY
    -0.09
    estre
    -0.09
    isten
    -0.09
    ìłģ
    -0.09
    deny
    -0.09
    ised
    -0.08
    POSITIVE LOGITS
    ypse
    0.16
    y
    0.14
    s
    0.14
    -thinking
    0.11
     thinking
    0.11
    /problem
    0.11
    aur
    0.11
    ipse
    0.10
    /me
    0.10
     disappearing
    0.10
    Activations Density 0.076%

    No Known Activations