© 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. 112023
    Prev
    Next
    INDEX
    Explanations

    place or put

    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
     Sullivan
    -0.10
     elsewhere
    -0.10
     trick
    -0.10
    crit
    -0.10
    CLS
    -0.09
     perv
    -0.09
     ex
    -0.09
     sew
    -0.09
    unden
    -0.09
    enis
    -0.09
    POSITIVE LOGITS
     headphones
    0.10
    translator
    0.08
     Ampl
    0.08
     pillows
    0.08
    acha
    0.08
     Helm
    0.08
    lator
    0.08
     palms
    0.08
     Sit
    0.08
     Therm
    0.08
    Activations Density 0.032%

    No Known Activations