© 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. 8071
    Prev
    Next
    INDEX
    Explanations

    Please inform

    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
     sam
    -0.06
     writ
    -0.06
    -↵
    -0.06
     pu
    -0.06
     cl
    -0.06
    alion
    -0.06
     Bes
    -0.05
     pik
    -0.05
     Nature
    -0.05
    arian
    -0.05
    POSITIVE LOGITS
     Strom
    0.14
     Buen
    0.12
     Castillo
    0.12
    busters
    0.12
    levator
    0.12
    inar
    0.12
    Enlarge
    0.12
     Angelo
    0.12
     HOWEVER
    0.12
    elper
    0.11
    Activations Density 0.008%

    No Known Activations