© 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. 91871
    Prev
    Next
    INDEX
    Explanations

    writing code or documentation

    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
     Vie
    -0.11
     style
    -0.10
     totaling
    -0.10
    STYLE
    -0.10
    ï¿
    -0.09
     maxi
    -0.09
     canceled
    -0.09
    COPY
    -0.09
    ów
    -0.08
    illos
    -0.08
    POSITIVE LOGITS
    orum
    0.10
     preced
    0.10
     precedence
    0.10
     precedent
    0.10
    emme
    0.10
     interf
    0.09
     calibrated
    0.09
     gn
    0.09
     orthogonal
    0.09
    preced
    0.09
    Activations Density 0.011%

    No Known Activations