© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 30062
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    iner
    -0.11
    ozo
    -0.09
     stale
    -0.09
    uale
    -0.09
    antry
    -0.09
     FOX
    -0.09
    ldr
    -0.09
     Birch
    -0.09
    bane
    -0.09
    uhan
    -0.09
    POSITIVE LOGITS
    .fastjson
    0.11
     Kong
    0.11
    isto
    0.11
    ĩ
    0.10
    arge
    0.09
    yan
    0.08
     ign
    0.08
     Disneyland
    0.08
    Translator
    0.08
    .ico
    0.08
    Activations Density 0.047%

    No Known Activations