© 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. 50165
    Prev
    Next
    INDEX
    Explanations

    November 1939

    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
    auc
    -0.09
     precip
    -0.09
    art
    -0.09
    åıĸæ¶Ī
    -0.08
     blunt
    -0.08
    acious
    -0.08
    ate
    -0.08
     gal
    -0.08
     Pell
    -0.08
     BACK
    -0.08
    POSITIVE LOGITS
     Mast
    0.09
     domina
    0.09
     Marino
    0.09
    owering
    0.09
     penetrating
    0.09
    .ba
    0.09
    opro
    0.08
     Marion
    0.08
     Pole
    0.08
    URY
    0.08
    Activations Density 0.001%

    No Known Activations