© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31444
    Prev
    Next
    INDEX
    Explanations

    shoulder Surgery

    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
    erial
    -0.12
    hta
    -0.12
    tings
    -0.12
    tle
    -0.11
    exual
    -0.11
    ete
    -0.11
    azon
    -0.10
    ym
    -0.10
    wel
    -0.10
    alog
    -0.10
    POSITIVE LOGITS
    /back
    0.12
     blade
    0.12
     blades
    0.12
    blade
    0.09
    /arm
    0.09
     Brent
    0.08
    (s
    0.08
    /head
    0.08
    oids
    0.08
     abbreviated
    0.07
    Activations Density 0.010%

    No Known Activations