© 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. 8233
    Prev
    Next
    INDEX
    Explanations

    starts sentences with "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
    hsi
    -0.10
    hel
    -0.10
    ele
    -0.10
     Tow
    -0.10
    haus
    -0.10
     "{{
    -0.10
    foy
    -0.10
     tum
    -0.10
    ãĢİ
    -0.09
     Caller
    -0.09
    POSITIVE LOGITS
    olation
    0.10
    adora
    0.09
    omers
    0.09
    olate
    0.09
    achsen
    0.09
    aurus
    0.08
    @Configuration
    0.08
    inya
    0.08
    ovich
    0.08
    iges
    0.08
    Activations Density 0.049%

    No Known Activations