© 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. 89361
    Prev
    Next
    INDEX
    Explanations

    answer depends

    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
     Shak
    -0.10
     Suddenly
    -0.10
    utto
    -0.10
     suddenly
    -0.10
     quadr
    -0.10
     Mes
    -0.10
     Energ
    -0.10
    iggs
    -0.10
     exit
    -0.09
     merely
    -0.09
    POSITIVE LOGITS
     Depends
    0.22
     depends
    0.21
    depends
    0.17
     depend
    0.16
     technically
    0.16
     Techn
    0.15
    Techn
    0.15
    Dep
    0.13
     honestly
    0.13
    Short
    0.13
    Activations Density 0.109%

    No Known Activations