© 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. 4226
    Prev
    Next
    INDEX
    Explanations

    storing information or handling files

    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
     lá
    -0.09
    nar
    -0.09
    una
    -0.09
     Mont
    -0.09
     endeavour
    -0.08
     volont
    -0.08
     alot
    -0.08
     ment
    -0.08
    .gg
    -0.08
     flagship
    -0.08
    POSITIVE LOGITS
    —to
    0.15
    /save
    0.14
     lest
    0.13
    /create
    0.13
    /start
    0.12
     properly
    0.11
    /be
    0.11
    OTH
    0.11
    /send
    0.10
    /find
    0.10
    Activations Density 1.407%

    No Known Activations