© 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. 111984
    Prev
    Next
    INDEX
    Explanations

    Posted in

    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
     Northeast
    -0.09
    elah
    -0.09
     inhab
    -0.08
    .inspect
    -0.08
    .stdin
    -0.08
     punct
    -0.08
    ptime
    -0.08
    inspection
    -0.08
    sert
    -0.08
     Pry
    -0.07
    POSITIVE LOGITS
    gee
    0.10
    oded
    0.10
     Fel
    0.10
     vide
    0.10
    ocks
    0.09
    (Frame
    0.09
     Coc
    0.09
    repeat
    0.09
     hos
    0.09
     Vir
    0.09
    Activations Density 0.002%

    No Known Activations