© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    complex concepts or terms

    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
    /Peak
    -0.10
    /slick
    -0.10
    igo
    -0.10
    /Dk
    -0.09
    ASP
    -0.09
    (or
    -0.09
    oho
    -0.09
     Mog
    -0.09
    à¹ī
    -0.08
     Ding
    -0.08
    POSITIVE LOGITS
     oraz
    0.32
     sowie
    0.29
     ainsi
    0.29
     plus
    0.27
     samt
    0.23
    ãĢģ
    0.22
     AND
    0.20
     nor
    0.20
    plus
    0.19
     coupled
    0.19
    Activations Density 5.705%

    No Known Activations