© 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. 90784
    Prev
    Next
    INDEX
    Explanations

    andy railway station

    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
    izu
    -0.09
    andr
    -0.08
     Cecil
    -0.08
    ظ
    -0.08
     \↵↵
    -0.08
     wm
    -0.07
     Nancy
    -0.07
     disposition
    -0.07
     Sever
    -0.07
     Sit
    -0.07
    POSITIVE LOGITS
     Heller
    0.11
    ugas
    0.11
    Spi
    0.10
     printable
    0.10
     Âł Âł Âł Âł
    0.10
     searchable
    0.10
     downloadable
    0.10
    Homepage
    0.10
    opi
    0.10
     pineapple
    0.10
    Activations Density 0.009%

    No Known Activations