© 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. 91894
    Prev
    Next
    INDEX
    Explanations

    conditional questions

    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
    aat
    -0.11
    apol
    -0.09
    ars
    -0.08
    uder
    -0.08
    Yaw
    -0.08
     Floyd
    -0.08
    ograd
    -0.07
     Ef
    -0.07
    nier
    -0.07
    avan
    -0.07
    POSITIVE LOGITS
     Are
    0.31
    Are
    0.30
    _are
    0.26
    are
    0.25
    —are
    0.25
    .are
    0.23
    ARE
    0.23
     ARE
    0.21
     sure
    0.21
    .Are
    0.20
    Activations Density 0.049%

    No Known Activations