© 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. 50379
    Prev
    Next
    INDEX
    Explanations

    introducing people or things

    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
    coration
    -0.12
    love
    -0.12
     inaug
    -0.12
     Daniels
    -0.12
     recourse
    -0.11
    bilt
    -0.11
     Jur
    -0.11
     Dia
    -0.11
    amic
    -0.11
    allo
    -0.11
    POSITIVE LOGITS
     formally
    0.17
     formal
    0.14
     properly
    0.13
     Formal
    0.12
    /register
    0.09
    /share
    0.08
     Wade
    0.08
     Glad
    0.08
    /form
    0.08
     herself
    0.08
    Activations Density 0.022%

    No Known Activations