© 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. 50324
    Prev
    Next
    INDEX
    Explanations

    digital or digital-related terms

    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
    kh
    -0.08
    arel
    -0.08
    omba
    -0.08
     Sommer
    -0.08
    MORE
    -0.08
    arez
    -0.07
    illac
    -0.07
     WC
    -0.07
     localize
    -0.07
     Fayette
    -0.07
    POSITIVE LOGITS
    /an
    0.18
     natives
    0.15
    ization
    0.14
    angi
    0.14
    ized
    0.13
    /opt
    0.13
    åĮĸ
    0.13
     twin
    0.12
    izing
    0.12
     humanities
    0.12
    Activations Density 0.144%

    No Known Activations