© 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. 117317
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    Negative Logits
    isy
    -0.08
     ima
    -0.08
    639
    -0.08
    è¿ĺ
    -0.08
     bore
    -0.08
     ÅŁ
    -0.08
     SMB
    -0.08
     incluso
    -0.08
     fakt
    -0.08
     pud
    -0.08
    POSITIVE LOGITS
    Ignore
    0.15
     ignore
    0.15
     Ignore
    0.14
    ignore
    0.14
     Those
    0.14
    gnore
    0.13
    Those
    0.13
     Known
    0.13
    "That
    0.12
     disregard
    0.12
    Activations Density 0.061%

    No Known Activations