© 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. 114792
    Prev
    Next
    INDEX
    Explanations

    Add information

    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
     bapt
    -0.10
     Giz
    -0.10
     Lon
    -0.10
     Mär
    -0.10
     Pu
    -0.09
    oria
    -0.09
    aha
    -0.09
    Lon
    -0.09
    pu
    -0.09
     Dyn
    -0.09
    POSITIVE LOGITS
    sass
    0.10
     gost
    0.09
     Claus
    0.08
    isma
    0.08
     Disco
    0.08
    obe
    0.08
     patter
    0.08
     ISI
    0.08
     bump
    0.08
    asper
    0.08
    Activations Density 0.001%

    No Known Activations