© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    ocr
    -0.11
     Shim
    -0.11
     "*"
    -0.10
    kowski
    -0.10
     Shen
    -0.10
     Moss
    -0.10
    otes
    -0.09
     consts
    -0.09
    ichi
    -0.09
    interop
    -0.09
    POSITIVE LOGITS
     something
    0.31
    something
    0.25
     Something
    0.22
    Something
    0.21
    omething
    0.17
     essentially
    0.17
     an
    0.17
     inherently
    0.17
     a
    0.16
     such
    0.16
    Activations Density 0.603%

    No Known Activations