© 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. 17679
    Prev
    Next
    INDEX
    Explanations

    case numbers or alphanumeric codes

    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
     cruc
    -0.09
     Ow
    -0.09
    wik
    -0.09
    omain
    -0.08
     cord
    -0.08
     Hobby
    -0.08
     puck
    -0.08
     PUSH
    -0.08
    vez
    -0.08
     filmy
    -0.08
    POSITIVE LOGITS
    adera
    0.11
    enu
    0.10
     Mund
    0.09
    CCR
    0.09
    mdi
    0.09
    Logged
    0.09
    ENU
    0.09
     touring
    0.09
    chine
    0.09
    ernen
    0.09
    Activations Density 0.201%

    No Known Activations