© 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. 18744
    Prev
    Next
    INDEX
    Explanations

    (if or optional

    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
    uten
    -0.12
     Arbitrary
    -0.11
    acho
    -0.10
    ovo
    -0.10
    tero
    -0.10
    ador
    -0.10
     Ty
    -0.10
    uer
    -0.10
    ona
    -0.10
    omen
    -0.10
    POSITIVE LOGITS
    (if
    0.35
    —if
    0.33
    /if
    0.32
    -if
    0.26
    —or
    0.26
     nonexistent
    0.24
    if
    0.21
    OrNull
    0.21
    /no
    0.20
    (optional
    0.20
    Activations Density 0.858%

    No Known Activations