© 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. 17387
    Prev
    Next
    INDEX
    Explanations

    informs or advises them

    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
     alive
    -0.09
    ayas
    -0.09
    iltr
    -0.09
     Mech
    -0.09
    094
    -0.09
     Sle
    -0.09
     Rick
    -0.09
    lew
    -0.09
    AV
    -0.08
    ces
    -0.08
    POSITIVE LOGITS
     about
    0.16
     of
    0.15
    about
    0.11
     verbally
    0.10
    _about
    0.10
     ABOUT
    0.09
    ifu
    0.09
     Watts
    0.09
    dao
    0.09
    .about
    0.09
    Activations Density 0.062%

    No Known Activations