© 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. 114816
    Prev
    Next
    INDEX
    Explanations

    expects parameter

    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
    itto
    -0.10
     Alternate
    -0.10
    ucs
    -0.10
     Clipboard
    -0.10
     unusually
    -0.09
     suddenly
    -0.09
     espec
    -0.09
     oddly
    -0.09
    âĢ³
    -0.09
     foregoing
    -0.09
    POSITIVE LOGITS
     originals
    0.16
     pristine
    0.13
     intact
    0.13
     elsewhere
    0.12
     untouched
    0.12
     simpler
    0.12
    original
    0.11
     ORIGINAL
    0.11
     autonomy
    0.11
     dazz
    0.11
    Activations Density 0.111%

    No Known Activations