© 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. 88099
    Prev
    Next
    INDEX
    Explanations

    <!DOCTYPE or âľĸ

    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
    ites
    -0.11
     Seam
    -0.10
     preferably
    -0.10
    eres
    -0.09
     baff
    -0.09
     Santana
    -0.09
    fac
    -0.09
    anted
    -0.09
     OWNER
    -0.09
     Tall
    -0.09
    POSITIVE LOGITS
    ħ
    0.10
    /o
    0.09
    (edit
    0.09
    -off
    0.09
     offs
    0.08
    ullo
    0.08
    ello
    0.08
     dok
    0.08
     undone
    0.08
    izu
    0.08
    Activations Density 0.015%

    No Known Activations