© 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. 28670
    Prev
    Next
    INDEX
    Explanations

    analyzing content, materials, or measurements

    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
     neighb
    -0.11
     enthusi
    -0.10
     foll
    -0.09
     sucess
    -0.09
     sadly
    -0.09
     INCLUDED
    -0.09
     gir
    -0.08
     GIR
    -0.08
     Provincial
    -0.08
     ={↵
    -0.08
    POSITIVE LOGITS
     unbe
    0.10
     oneself
    0.10
    Therefore
    0.10
    apo
    0.09
     transcend
    0.09
    ;/*
    0.09
    ogr
    0.09
    Sky
    0.09
     hereby
    0.09
     peculiar
    0.08
    Activations Density 0.014%

    No Known Activations