© 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. 47380
    Prev
    Next
    INDEX
    Explanations

    formulas, code, and separators

    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
    -
    -0.09
    ount
    -0.08
    (
    -0.08
     circ
    -0.08
     uncont
    -0.07
     Woods
    -0.07
    HL
    -0.06
    /c
    -0.06
    row
    -0.06
     awake
    -0.06
    POSITIVE LOGITS
    webkit
    0.18
    ~-
    0.17
    =-=-=-=-=-=-=-=-
    0.14
    =-=-
    0.14
    eba
    0.14
    ~-~-~-~-
    0.13
    +-+-
    0.13
    +-+-+-+-+-+-+-+-
    0.13
    moz
    0.13
    ~-~-
    0.13
    Activations Density 0.076%

    No Known Activations