© 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. 113703
    Prev
    Next
    INDEX
    Explanations

    credibility, authority, respect, recognition

    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
    vil
    -0.10
    ariant
    -0.10
    eler
    -0.09
    dsa
    -0.09
    sla
    -0.09
     thanking
    -0.09
    antha
    -0.09
    anno
    -0.09
    olor
    -0.09
    /container
    -0.09
    POSITIVE LOGITS
     credibility
    0.72
     legitimacy
    0.52
     credible
    0.50
     cred
    0.37
     legitim
    0.36
     legit
    0.34
     authority
    0.33
    cred
    0.32
    credible
    0.32
     respected
    0.31
    Activations Density 0.354%

    No Known Activations