© 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. 26408
    Prev
    Next
    INDEX
    Explanations

    links to images and media

    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
    .ActionListener
    -0.12
    .RequestMapping
    -0.10
    еÑĪ
    -0.10
    nev
    -0.09
    ipay
    -0.09
    dition
    -0.09
     acrylic
    -0.09
    datal
    -0.09
     COPYING
    -0.09
    kode
    -0.08
    POSITIVE LOGITS
     vids
    0.12
     bump
    0.09
    ĥģ
    0.08
     Nack
    0.08
    hausen
    0.08
     Affero
    0.08
    resp
    0.08
     wanna
    0.08
    Ø·
    0.08
     Awesome
    0.07
    Activations Density 0.053%

    No Known Activations