© 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. 17330
    Prev
    Next
    INDEX
    Explanations

    produced by, acquired by, succeeded by

    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
     fino
    -0.10
    ider
    -0.09
    legate
    -0.09
    AVOR
    -0.09
    ynet
    -0.09
     Cater
    -0.09
     Cro
    -0.09
     ur
    -0.09
    iness
    -0.08
     endors
    -0.08
    POSITIVE LOGITS
    /rec
    0.11
     successfully
    0.11
     unsus
    0.10
     sed
    0.10
     Innoc
    0.10
    uced
    0.10
     neighbourhood
    0.10
     tempted
    0.09
     temptation
    0.09
     handsome
    0.09
    Activations Density 0.003%

    No Known Activations