© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90223
    Prev
    Next
    INDEX
    Explanations

    shy or timid personality

    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
     satisfying
    -0.11
     tempting
    -0.11
     hatred
    -0.11
     inev
    -0.11
     trivial
    -0.11
     Furious
    -0.11
     knowingly
    -0.10
     Heading
    -0.10
     cheating
    -0.10
     insulting
    -0.10
    POSITIVE LOGITS
     shy
    0.52
     timid
    0.41
     intro
    0.29
     bash
    0.28
     quiet
    0.26
     quieter
    0.24
     Intro
    0.24
     Quiet
    0.23
    quiet
    0.22
     hesitant
    0.22
    Activations Density 0.086%

    No Known Activations