© 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. 115212
    Prev
    Next
    INDEX
    Explanations

    authors and names

    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
     Dann
    -0.12
     GURL
    -0.12
    hai
    -0.10
     dai
    -0.10
     SOP
    -0.10
     Eag
    -0.10
    yny
    -0.09
    .dd
    -0.09
     hete
    -0.09
    ,)↵
    -0.09
    POSITIVE LOGITS
     aka
    0.09
     “
    0.08
    tag
    0.08
     Cardinal
    0.08
     Peaks
    0.08
    zilla
    0.08
     Tib
    0.08
     nicknamed
    0.08
     nickname
    0.08
     Plays
    0.07
    Activations Density 0.034%

    No Known Activations