© 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. 115681
    Prev
    Next
    INDEX
    Explanations

    names of places or 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
     dire
    -0.12
    oya
    -0.11
     provincial
    -0.11
    iei
    -0.11
    lea
    -0.11
     hete
    -0.11
    ensi
    -0.11
     Revel
    -0.11
    ensely
    -0.11
     warmth
    -0.11
    POSITIVE LOGITS
     concession
    0.08
     bush
    0.08
    Unnamed
    0.08
     taper
    0.08
     US
    0.08
     Hoffman
    0.07
    .US
    0.07
     reversal
    0.07
     USDA
    0.06
     slab
    0.06
    Activations Density 0.763%

    No Known Activations