© 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. 47132
    Prev
    Next
    INDEX
    Explanations

    code comments or definitions

    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
     frags
    -0.11
     Carlson
    -0.10
     unlink
    -0.10
    )--
    -0.10
     todd
    -0.10
     hete
    -0.10
     tremend
    -0.10
     horm
    -0.10
     Peek
    -0.10
     kot
    -0.10
    POSITIVE LOGITS
     —
    0.18
     extrem
    0.12
     shall
    0.12
     /*
    0.12
    ;/*
    0.12
    /*
    0.11
    (/*
    0.10
    âĢIJ
    0.08
     —↵↵
    0.08
    ————
    0.08
    Activations Density 0.008%

    No Known Activations