© 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. 18057
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or words

    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
    CTRL
    -0.08
     repeating
    -0.08
    istan
    -0.07
    itto
    -0.07
    cox
    -0.07
    rox
    -0.07
     Kiss
    -0.07
     Cru
    -0.07
     Nic
    -0.06
     Again
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤ¸
    0.12
     —↵↵
    0.11
    yla
    0.11
     groove
    0.11
    Offsets
    0.10
     Spi
    0.10
    eka
    0.10
    yi
    0.10
    ually
    0.10
     SPI
    0.10
    Activations Density 0.001%

    No Known Activations