© 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. 50380
    Prev
    Next
    INDEX
    Explanations

    symbols and code delimiters

    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
     Yankee
    -0.08
     ÂŃ
    -0.07
    Âł
    -0.07
     airborne
    -0.07
    heel
    -0.07
     revamped
    -0.07
     customized
    -0.07
     rhyme
    -0.07
     aggrav
    -0.07
    Ìģ
    -0.07
    POSITIVE LOGITS
     wich
    0.13
    ing
    0.12
     corres
    0.11
     tud
    0.11
     confort
    0.11
    ÑĤом
    0.10
    atel
    0.10
    Away
    0.10
    hek
    0.10
    orman
    0.10
    Activations Density 0.010%

    No Known Activations