© 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. 116582
    Prev
    Next
    INDEX
    Explanations

    computer supported cooperative work

    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
    cis
    -0.06
    arma
    -0.06
     beaut
    -0.06
    orc
    -0.06
     vars
    -0.06
     scav
    -0.06
    quisition
    -0.06
     Saunders
    -0.06
     Sala
    -0.06
    Reporter
    -0.06
    POSITIVE LOGITS
     Poz
    0.12
     gladly
    0.12
     Adrian
    0.11
    ipi
    0.11
    994
    0.11
    [of
    0.11
     proudly
    0.10
    /schema
    0.10
     showMessage
    0.10
     liberated
    0.10
    Activations Density 0.001%

    No Known Activations