© 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. 49746
    Prev
    Next
    INDEX
    Explanations

    Version 1.0

    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
    emax
    -0.11
     Intercept
    -0.10
     inadvert
    -0.10
     Neb
    -0.10
     lur
    -0.10
    iben
    -0.10
     anonymous
    -0.09
    ero
    -0.09
    /***/
    -0.09
    aroo
    -0.09
    POSITIVE LOGITS
     Voll
    0.08
     eof
    0.08
    marvin
    0.08
    ICES
    0.08
    sbin
    0.08
     gord
    0.08
    WEST
    0.08
    stdafx
    0.08
    č↵↵
    0.08
    _orig
    0.07
    Activations Density 0.005%

    No Known Activations