© 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. 32335
    Prev
    Next
    INDEX
    Explanations

    questions starting with "are" or "were"

    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
    Chi
    -0.12
    DDS
    -0.11
    reira
    -0.11
    bbc
    -0.11
     cue
    -0.11
    ogo
    -0.11
     TWO
    -0.11
    brit
    -0.11
     jointly
    -0.11
    maf
    -0.11
    POSITIVE LOGITS
     most
    0.08
     there
    0.07
     geomet
    0.07
     Rox
    0.07
    istor
    0.06
     Santa
    0.06
     fy
    0.06
     Altern
    0.06
     older
    0.06
     darn
    0.06
    Activations Density 0.001%

    No Known Activations