© 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. 46809
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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
    olute
    -0.08
    uze
    -0.07
    stream
    -0.07
    -opt
    -0.07
     Tail
    -0.07
     ca
    -0.07
     Lv
    -0.07
    (prob
    -0.07
     Cab
    -0.07
    obra
    -0.07
    POSITIVE LOGITS
     Clem
    0.13
    499
    0.11
     Barg
    0.10
    stand
    0.10
    ician
    0.10
    _below
    0.10
     Gemini
    0.09
    999
    0.09
     zer
    0.09
     upstream
    0.09
    Activations Density 0.070%

    No Known Activations