© 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. 50239
    Prev
    Next
    INDEX
    Explanations

    Âł

    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
    %E
    -0.09
    ([↵
    -0.09
    ...
    -0.09
    -Semit
    -0.08
    -
    -0.08
     (↵↵
    -0.08
     â
    -0.08
    \(
    -0.08
    ----
    -0.08
    POSITIVE LOGITS
    Âł
    0.73
    Âł↵
    0.32
    &nbsp
    0.32
    ³³
    0.28
    0.25
    0.23
    0.23
    âĢ
    0.22
    ãĢĢ
    0.22
    \xa
    0.22
    Activations Density 1.892%

    No Known Activations