© 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. 14567
    Prev
    Next
    INDEX
    Explanations

    high status or authority

    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
     realistic
    -0.09
    arti
    -0.09
    Lock
    -0.09
     Bride
    -0.09
     Responsive
    -0.09
     mechanical
    -0.09
    ä»Ĭå¹´
    -0.09
     Raq
    -0.09
     substitute
    -0.09
     paradise
    -0.09
    POSITIVE LOGITS
     VIP
    0.28
     rank
    0.24
    VIP
    0.24
     authority
    0.23
     privileged
    0.22
     royalty
    0.22
     influential
    0.22
     senior
    0.20
     stature
    0.20
     dign
    0.20
    Activations Density 0.244%

    No Known Activations