© 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. 28690
    Prev
    Next
    INDEX
    Explanations

    up/down regulation

    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
    Nat
    -0.08
     brisk
    -0.08
    abbr
    -0.08
     Crisis
    -0.08
    iat
    -0.07
    Asked
    -0.07
    iglia
    -0.07
    elin
    -0.07
     Nat
    -0.07
    pline
    -0.07
    POSITIVE LOGITS
    /down
    0.23
    /up
    0.20
    -down
    0.15
     downs
    0.14
    (down
    0.13
    DOWN
    0.12
     ante
    0.12
    (up
    0.12
    Down
    0.11
    _DOWN
    0.11
    Activations Density 0.128%

    No Known Activations