© 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. 112213
    Prev
    Next
    INDEX
    Explanations

    hidden facts and details

    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
     unavoidable
    -0.11
    ulen
    -0.09
    uras
    -0.08
    orm
    -0.08
     Skinny
    -0.08
     ongoing
    -0.08
    ura
    -0.08
    udas
    -0.08
     Overview
    -0.08
     Bes
    -0.07
    POSITIVE LOGITS
     treasures
    0.23
     treasure
    0.19
     gems
    0.17
     gem
    0.17
     territory
    0.17
     secrets
    0.16
     depths
    0.16
     territories
    0.15
     Gems
    0.14
    /un
    0.14
    Activations Density 0.035%

    No Known Activations