© 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. 6686
    Prev
    Next
    INDEX
    Explanations

    tree parts

    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
    mente
    -0.08
     refere
    -0.08
     fert
    -0.08
    ned
    -0.08
    wl
    -0.08
    utex
    -0.07
    st
    -0.07
     Vale
    -0.07
    Cong
    -0.07
    cing
    -0.07
    POSITIVE LOGITS
     stump
    0.20
     trunk
    0.17
     bark
    0.16
    cko
    0.13
     limb
    0.13
    /tree
    0.12
     branch
    0.12
    -lined
    0.12
    house
    0.12
    .Tree
    0.12
    Activations Density 0.029%

    No Known Activations