© 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. 26425
    Prev
    Next
    INDEX
    Explanations

    perfect or right noun

    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
    iar
    -0.12
    opr
    -0.11
    erland
    -0.11
     Kis
    -0.10
    /preferences
    -0.10
    abble
    -0.10
    uze
    -0.10
     estates
    -0.10
     recess
    -0.10
    rtl
    -0.10
    POSITIVE LOGITS
     for
    0.12
    (s
    0.12
     combination
    0.11
     imaginable
    0.10
     su
    0.10
     suited
    0.10
    su
    0.10
     match
    0.09
     depending
    0.09
    (es
    0.09
    Activations Density 0.090%

    No Known Activations