© 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. 116191
    Prev
    Next
    INDEX
    Explanations

    patching

    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
    ff
    -0.10
    asl
    -0.10
    inx
    -0.10
     flushing
    -0.10
     Gib
    -0.10
    adro
    -0.10
    ativ
    -0.10
    /stretch
    -0.10
    æĢģ
    -0.09
    uter
    -0.09
    POSITIVE LOGITS
     patch
    0.17
    work
    0.16
     patches
    0.15
     Patch
    0.15
    (patch
    0.14
     patched
    0.12
    patch
    0.12
    Patch
    0.12
    y
    0.12
    werk
    0.11
    Activations Density 0.018%

    No Known Activations