© 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. 92120
    Prev
    Next
    INDEX
    Explanations

    new direction or era

    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
    ABCDEFGHI
    -0.10
    abcdefghijkl
    -0.08
    abcdefghijklmnop
    -0.08
     sucess
    -0.08
    artz
    -0.08
    ?↵↵↵↵
    -0.08
    ⣩
    -0.08
     mee
    -0.07
    arton
    -0.07
    /goto
    -0.07
    POSITIVE LOGITS
     [...]
    0.19
     (...)
    0.19
     [âĢ¦]
    0.18
    [âĢ¦]
    0.17
    [,]
    0.15
    ."</
    0.13
    ô
    0.13
     [...
    0.12
     [
    0.12
    âĢIJ
    0.11
    Activations Density 2.830%

    No Known Activations