© 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. 26094
    Prev
    Next
    INDEX
    Explanations

    dragon followed by descriptions

    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
    .crm
    -0.11
    otel
    -0.10
    ãĥ¡ãĥ³ãĥĪ
    -0.10
    esa
    -0.10
    urre
    -0.10
     Trafford
    -0.10
    /pages
    -0.10
    iotics
    -0.10
    cheid
    -0.10
    maal
    -0.09
    POSITIVE LOGITS
    fly
    0.21
    flies
    0.19
    layers
    0.13
    Fly
    0.10
     Slayer
    0.10
    layer
    0.10
    -fly
    0.10
     fly
    0.09
    cale
    0.09
    fruit
    0.09
    Activations Density 0.013%

    No Known Activations