© 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. 3384
    Prev
    Next
    INDEX
    Explanations

    of

    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
     filmy
    -0.08
    LogFile
    -0.08
     Wolfe
    -0.08
     paw
    -0.08
    chor
    -0.08
     Kaw
    -0.08
    cth
    -0.08
    eel
    -0.07
    ynes
    -0.07
    iens
    -0.07
    POSITIVE LOGITS
    -of
    0.28
     of
    0.19
    _of
    0.18
     даннÑĭÑħ
    0.15
    OfWork
    0.14
    _OF
    0.12
    _Of
    0.11
    OfClass
    0.11
     thereof
    0.11
    OfString
    0.11
    Activations Density 1.104%

    No Known Activations