© 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. 33212
    Prev
    Next
    INDEX
    Explanations

    groups of people and places

    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
     my
    -0.09
    aza
    -0.09
     wonderful
    -0.08
     buddies
    -0.08
     his
    -0.08
     juste
    -0.08
     flair
    -0.07
     Santo
    -0.07
     courts
    -0.07
     rings
    -0.07
    POSITIVE LOGITS
    —including
    0.16
     are
    0.16
     alike
    0.14
     have
    0.13
    —from
    0.13
     outnumber
    0.12
     protested
    0.12
     often
    0.12
     disproportionately
    0.12
    often
    0.12
    Activations Density 0.022%

    No Known Activations