© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46726
    Prev
    Next
    INDEX
    Explanations

    online services

    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
    ãģ
    -0.08
     Dol
    -0.08
     rank
    -0.08
     Doll
    -0.08
     manual
    -0.07
    ome
    -0.07
     younger
    -0.07
    ire
    -0.07
     interpre
    -0.07
     live
    -0.07
    POSITIVE LOGITS
     nowadays
    0.12
    /star
    0.12
    Places
    0.11
    /port
    0.11
    /mobile
    0.11
     Broad
    0.11
    mailer
    0.10
     vulgar
    0.10
    inden
    0.10
     tong
    0.10
    Activations Density 0.025%

    No Known Activations