© 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. 89636
    Prev
    Next
    INDEX
    Explanations

    BuildActionEntry, Frontliner, GroupBox, managerFile

    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
    ripp
    -0.08
     Pens
    -0.07
    hashtags
    -0.07
    allet
    -0.07
     Waters
    -0.07
    -vis
    -0.07
     dancers
    -0.07
     Patterson
    -0.07
    markers
    -0.07
    icopt
    -0.07
    POSITIVE LOGITS
    categorie
    0.11
    indrome
    0.11
    clide
    0.11
     Farr
    0.11
    TCHA
    0.11
    VEC
    0.11
    FTA
    0.10
     Kahn
    0.10
    ovo
    0.10
    irk
    0.10
    Activations Density 1.221%

    No Known Activations