© 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. 32387
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     versus
    -0.08
    âĨIJ
    -0.08
     chorus
    -0.07
    usch
    -0.07
     Chron
    -0.07
     intent
    -0.07
     Pee
    -0.07
     reliance
    -0.07
     ple
    -0.06
     VS
    -0.06
    POSITIVE LOGITS
     (@
    0.14
     topping
    0.13
     @_
    0.12
     nich
    0.12
     tik
    0.12
     Dann
    0.12
     Blessed
    0.11
    Writes
    0.11
     unquestion
    0.11
    leh
    0.11
    Activations Density 0.002%

    No Known Activations