© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 49740
    Prev
    Next
    INDEX
    Explanations

    44

    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
    nement
    -0.11
    ing
    -0.10
    odic
    -0.10
    uator
    -0.10
    uous
    -0.09
    etri
    -0.09
    ning
    -0.09
     honest
    -0.09
     ning
    -0.09
    uously
    -0.08
    POSITIVE LOGITS
     Magnum
    0.13
    è®®
    0.13
    faction
    0.11
    ¤í
    0.10
    idge
    0.10
    pie
    0.10
    chia
    0.10
    unately
    0.10
    ertation
    0.10
    oste
    0.10
    Activations Density 0.075%

    No Known Activations