© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50709
    Prev
    Next
    INDEX
    Explanations

    course of

    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
     Warren
    -0.08
    lei
    -0.08
    anka
    -0.07
     interim
    -0.07
     partial
    -0.07
    ör
    -0.07
     sort
    -0.06
     FAST
    -0.06
    alc
    -0.06
    byn
    -0.06
    POSITIVE LOGITS
     Lent
    0.13
     conversation
    0.13
     Conversation
    0.12
    (es
    0.12
    Conversation
    0.12
     Convers
    0.12
     conversations
    0.12
     Bloss
    0.11
    eps
    0.11
    kim
    0.11
    Activations Density 0.038%

    No Known Activations