© 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. 7934
    Prev
    Next
    INDEX
    Explanations

    att followed by a word fragment

    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
    nut
    -0.10
     scatter
    -0.09
     Scatter
    -0.08
    filled
    -0.08
    periment
    -0.08
    tee
    -0.08
    ingly
    -0.08
    hs
    -0.08
    Nut
    -0.08
     Highest
    -0.07
    POSITIVE LOGITS
     att
    0.19
     Att
    0.15
     Attachment
    0.15
    ENTION
    0.15
    .Att
    0.14
    (att
    0.14
     attachment
    0.14
    itudes
    0.13
    uned
    0.13
     Accom
    0.13
    Activations Density 0.016%

    No Known Activations