© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48037
    Prev
    Next
    INDEX
    Explanations

    can be

    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
     didn
    -0.11
    didn
    -0.11
     knew
    -0.10
    ynes
    -0.10
    ắ
    -0.10
    .exists
    -0.10
    617
    -0.10
     threw
    -0.10
    987
    -0.10
     gave
    -0.10
    POSITIVE LOGITS
    è¢
    0.29
    를
    0.22
    ãĤĴ
    0.22
     Äijược
    0.20
     being
    0.19
     undergo
    0.19
    ìĿĦ
    0.18
     worden
    0.18
     zosta
    0.18
     wurde
    0.17
    Activations Density 2.933%

    No Known Activations