© 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. 15726
    Prev
    Next
    INDEX
    Explanations

    up

    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
    cent
    -0.11
    kers
    -0.09
     Assigned
    -0.09
    /chart
    -0.08
    GING
    -0.08
    /trans
    -0.08
    onet
    -0.08
    ulo
    -0.08
    elper
    -0.08
    Nat
    -0.08
    POSITIVE LOGITS
     up
    0.16
    -up
    0.13
    -down
    0.13
     upfront
    0.13
    _up
    0.13
    UpDown
    0.13
    upa
    0.12
     upt
    0.12
     until
    0.12
     upto
    0.12
    Activations Density 0.032%

    No Known Activations