© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    Curtis names and words

    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
    kle
    -0.10
     indefinitely
    -0.09
    ratio
    -0.08
    zyst
    -0.08
     alarm
    -0.08
    NB
    -0.08
    ipo
    -0.08
     Shoe
    -0.08
    psilon
    -0.08
     easy
    -0.08
    POSITIVE LOGITS
    leck
    0.10
    iled
    0.10
    ard
    0.10
    ards
    0.10
    feld
    0.10
    /wait
    0.09
    ص
    0.09
    riet
    0.09
     cruising
    0.09
    NoSuch
    0.09
    Activations Density 0.001%

    No Known Activations