© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7977
    Prev
    Next
    INDEX
    Explanations

    list introducers

    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
     pres
    -0.08
     vog
    -0.08
    itten
    -0.08
    macros
    -0.08
    iti
    -0.08
    #+
    -0.08
     [{
    -0.08
    ELL
    -0.08
     obt
    -0.08
     Ve
    -0.08
    POSITIVE LOGITS
     including
    0.39
     include
    0.29
     includ
    0.29
    including
    0.29
     such
    0.27
     Including
    0.26
    Including
    0.25
     INCLUDING
    0.25
     includes
    0.25
    such
    0.21
    Activations Density 1.066%

    No Known Activations