© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31816
    Prev
    Next
    INDEX
    Explanations

    legal and social topics

    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
     Walter
    -0.08
     tim
    -0.07
     Pu
    -0.07
     Walters
    -0.07
    .Pos
    -0.06
    ovsky
    -0.06
     Hoffman
    -0.06
     Adler
    -0.06
     Vog
    -0.06
    adan
    -0.06
    POSITIVE LOGITS
    odash
    0.11
    lland
    0.11
    MT
    0.10
    ิà¸Ļ
    0.10
    anmar
    0.10
     sight
    0.10
    chs
    0.10
    ipl
    0.10
    orm
    0.10
    uest
    0.10
    Activations Density 2.892%

    No Known Activations