© 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. 49778
    Prev
    Next
    INDEX
    Explanations

    terminated by colon

    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
     =",
    -0.10
    |i
    -0.10
    {o
    -0.10
     -,
    -0.09
    ;n
    -0.09
    >{
    -0.09
    destruct
    -0.09
     dust
    -0.09
    loth
    -0.09
     clums
    -0.09
    POSITIVE LOGITS
    :
    0.32
    :maj
    0.22
    :variables
    0.18
    ï¼ļ
    0.17
    :↵
    0.17
    :.
    0.16
    :,
    0.15
    :</
    0.15
    :mm
    0.15
    :↵↵
    0.14
    Activations Density 0.803%

    No Known Activations