© 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. 90894
    Prev
    Next
    INDEX
    Explanations

    embarrassing and disappointing contexts

    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
    tings
    -0.12
     Wah
    -0.09
     Millenn
    -0.09
     predominant
    -0.09
    kommen
    -0.09
    olis
    -0.09
     Gat
    -0.09
    -remove
    -0.09
    ali
    -0.08
    haul
    -0.08
    POSITIVE LOGITS
    ingly
    0.16
     embarrassing
    0.12
     embar
    0.10
     whisk
    0.10
    ãģĿ
    0.10
     embarrass
    0.10
    usi
    0.10
     embarrassed
    0.10
     embarrassment
    0.09
     lud
    0.09
    Activations Density 0.003%

    No Known Activations