© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29430
    Prev
    Next
    INDEX
    Explanations

    fun and engaging environment

    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
    icot
    -0.13
     everywhere
    -0.13
     Everywhere
    -0.13
    uye
    -0.11
     accidental
    -0.10
     onwards
    -0.10
    /internal
    -0.10
     unless
    -0.10
    еÑĢж
    -0.10
    sass
    -0.10
    POSITIVE LOGITS
     safely
    0.20
     without
    0.16
     uninterrupted
    0.13
    without
    0.13
     supervised
    0.13
     lux
    0.12
     securely
    0.12
     while
    0.12
     safe
    0.11
     controlled
    0.11
    Activations Density 0.262%

    No Known Activations