© 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. 92313
    Prev
    Next
    INDEX
    Explanations

    Copyright or pricing information

    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
     Hose
    -0.09
    acd
    -0.08
     Podesta
    -0.08
     rounds
    -0.08
     distortion
    -0.08
     Summit
    -0.07
     hust
    -0.07
     circulation
    -0.07
     paran
    -0.07
    097
    -0.07
    POSITIVE LOGITS
     testify
    0.10
     catch
    0.10
     Adler
    0.10
     marked
    0.10
    tl
    0.09
    ặ
    0.09
    moth
    0.09
     distinguished
    0.09
     outnumber
    0.09
     mach
    0.09
    Activations Density 0.057%

    No Known Activations