© 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. 4173
    Prev
    Next
    INDEX
    Explanations

    enable or access

    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
    Streamer
    -0.11
    MIC
    -0.10
     /^\
    -0.10
     anc
    -0.10
    aghan
    -0.10
    IDX
    -0.10
     ur
    -0.10
    mw
    -0.10
    rette
    -0.10
     SEX
    -0.10
    POSITIVE LOGITS
     peak
    0.08
     Mansion
    0.07
    mys
    0.07
     overdue
    0.07
     Peak
    0.07
     Trib
    0.07
     enable
    0.07
     hosted
    0.07
     med
    0.07
     internal
    0.07
    Activations Density 0.002%

    No Known Activations