© 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. 91885
    Prev
    Next
    INDEX
    Explanations

    encyclopedia, Wiki, orphometrics

    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
     Het
    -0.10
    XT
    -0.10
    ossier
    -0.09
    fest
    -0.09
    keit
    -0.09
     characterized
    -0.09
    arcy
    -0.09
     unsuccessfully
    -0.09
     STA
    -0.09
     Transmission
    -0.09
    POSITIVE LOGITS
    nee
    0.10
     smith
    0.09
    indy
    0.09
    versation
    0.08
     Shade
    0.08
     Parkinson
    0.08
     opposite
    0.08
    unsigned
    0.08
    aban
    0.08
     lax
    0.08
    Activations Density 0.001%

    No Known Activations