© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114901
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    .JOptionPane
    -0.09
     srand
    -0.08
     ply
    -0.07
     Plymouth
    -0.07
     damp
    -0.07
    ظ
    -0.07
     fuel
    -0.07
     fatal
    -0.07
     freely
    -0.06
     dimin
    -0.06
    POSITIVE LOGITS
     Curtain
    0.11
    .NonNull
    0.11
     onPostExecute
    0.10
    ooter
    0.10
    .opensource
    0.10
    aura
    0.10
     refl
    0.10
    archives
    0.10
    .InputStreamReader
    0.10
    .JSONArray
    0.09
    Activations Density 0.724%

    No Known Activations