© 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. 112963
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
     fresh
    -0.08
    fresh
    -0.07
     Lap
    -0.07
     freshly
    -0.07
    _places
    -0.07
    falls
    -0.07
     Atomic
    -0.06
    -UA
    -0.06
     peg
    -0.06
    estr
    -0.06
    POSITIVE LOGITS
    .RequestBody
    0.13
    .ActionListener
    0.12
     whipping
    0.11
    /type
    0.11
     instrumental
    0.11
    aket
    0.10
    netinet
    0.10
    webkit
    0.10
    subpackage
    0.10
    iets
    0.10
    Activations Density 0.096%

    No Known Activations