© 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. 14549
    Prev
    Next
    INDEX
    Explanations

    when is it used or defined

    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
    uchen
    -0.11
     Fletcher
    -0.11
    ott
    -0.10
    uces
    -0.10
     gro
    -0.10
    utas
    -0.10
    ëĶ
    -0.10
     partially
    -0.10
     Ferr
    -0.10
    unde
    -0.09
    POSITIVE LOGITS
    ?
    0.20
    —is
    0.17
    ?,
    0.16
    ?↵↵↵↵↵↵
    0.16
    —are
    0.16
    ?"↵↵↵↵
    0.14
    ?,↵
    0.14
     Does
    0.14
    ?).
    0.14
    ?.
    0.14
    Activations Density 0.507%

    No Known Activations