© 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. 27103
    Prev
    Next
    INDEX
    Explanations

    almost certainly / ...ally every / ... victoria during

    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
     passports
    -0.09
    SES
    -0.09
    orary
    -0.09
     baj
    -0.08
    rror
    -0.08
    uguay
    -0.08
     thermo
    -0.08
     ballot
    -0.08
    leston
    -0.08
    uhl
    -0.08
    POSITIVE LOGITS
    unread
    0.15
     nearly
    0.12
     almost
    0.12
     reaching
    0.12
     overs
    0.12
    ancel
    0.11
     finished
    0.11
     kunt
    0.10
    almost
    0.10
     taller
    0.10
    Activations Density 0.001%

    No Known Activations