© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    numbers after separators

    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
    alis
    -0.12
    979
    -0.09
     fav
    -0.09
    ,but
    -0.09
    _online
    -0.09
    unic
    -0.09
     Baz
    -0.09
     meaningful
    -0.09
     {}",
    -0.08
     Rog
    -0.08
    POSITIVE LOGITS
    olle
    0.10
     reversible
    0.10
     Personally
    0.09
    åī
    0.09
     lasting
    0.09
     bounce
    0.09
     numbered
    0.09
     putt
    0.09
     Rudy
    0.09
    UTE
    0.08
    Activations Density 0.087%

    No Known Activations