© 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. 50253
    Prev
    Next
    INDEX
    Explanations

    company or service names

    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
    uae
    -0.09
     comprised
    -0.08
     booster
    -0.07
    WE
    -0.07
    rey
    -0.07
    ues
    -0.07
    -color
    -0.07
     Tau
    -0.07
     capsule
    -0.07
    idos
    -0.07
    POSITIVE LOGITS
     chat
    0.14
    chat
    0.12
    MapView
    0.11
    achat
    0.11
    dash
    0.11
     geo
    0.11
    .CH
    0.10
    ourg
    0.10
    kart
    0.10
    Tk
    0.10
    Activations Density 0.001%

    No Known Activations