© 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. 18034
    Prev
    Next
    INDEX
    Explanations

    app/config/views/spec

    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
     Laure
    -0.09
     Balt
    -0.08
    onom
    -0.08
     Figures
    -0.08
     figures
    -0.08
    .byte
    -0.08
    elon
    -0.08
     aspir
    -0.08
     Merch
    -0.08
     Wave
    -0.08
    POSITIVE LOGITS
    (optional
    0.12
    /non
    0.10
     dri
    0.10
    /place
    0.10
    ?key
    0.10
     Pending
    0.10
    rende
    0.09
     Maiden
    0.09
    bak
    0.09
     serialVersionUID
    0.09
    Activations Density 0.006%

    No Known Activations