© 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. 17384
    Prev
    Next
    INDEX
    Explanations

    // Part of the LLVM Project

    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
     McCl
    -0.11
     REPL
    -0.10
    arez
    -0.10
    -but
    -0.10
    /of
    -0.09
     Sax
    -0.09
    imb
    -0.09
    _BB
    -0.09
    oret
    -0.09
    ajo
    -0.09
    POSITIVE LOGITS
     habit
    0.09
     Ste
    0.09
     comb
    0.08
     Cot
    0.08
     christmas
    0.08
     Greenwood
    0.08
     postpon
    0.08
    pas
    0.08
     surviving
    0.08
     Morton
    0.08
    Activations Density 0.005%

    No Known Activations