© 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. 4368
    Prev
    Next
    INDEX
    Explanations

    lists or

    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
    ãĢģ
    -0.10
     muster
    -0.09
     mitt
    -0.09
     Sn
    -0.09
    rier
    -0.09
    .shtml
    -0.08
     #[
    -0.08
     hors
    -0.08
     unsure
    -0.08
     unthinkable
    -0.08
    POSITIVE LOGITS
    aze
    0.09
    locals
    0.08
     UNUSED
    0.08
     Rational
    0.08
     scarc
    0.08
     Kul
    0.08
    ober
    0.08
     Oscar
    0.08
    nin
    0.08
     Erick
    0.08
    Activations Density 0.033%

    No Known Activations