© 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. 33294
    Prev
    Next
    INDEX
    Explanations

    code comments and markers

    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
     —
    -0.13
    ãĢĮ
    -0.12
    ——
    -0.09
     fav
    -0.09
    laus
    -0.09
    ied
    -0.09
    ieres
    -0.08
    –
    -0.08
    Ñİ
    -0.08
     vic
    -0.08
    POSITIVE LOGITS
    a
    0.17
    //--
    0.16
    "--
    0.16
    ->
    0.15
    /--
    0.14
     --
    0.14
    s
    0.13
    y
    0.13
    |--
    0.13
    .--
    0.12
    Activations Density 0.342%

    No Known Activations