© 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. 15296
    Prev
    Next
    INDEX
    Explanations

    questions about potential

    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
     prelim
    -0.12
    -fashion
    -0.12
    /manage
    -0.11
    imd
    -0.11
    -exec
    -0.10
    ÑĢÑĥк
    -0.10
     nim
    -0.10
    rame
    -0.10
    /null
    -0.10
    Disposed
    -0.10
    POSITIVE LOGITS
     works
    0.18
     Works
    0.17
     ever
    0.14
     really
    0.13
    Works
    0.12
     Really
    0.11
     WORK
    0.10
     affect
    0.10
    works
    0.10
     hurt
    0.10
    Activations Density 0.028%

    No Known Activations