© 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. 50505
    Prev
    Next
    INDEX
    Explanations

    states of being or obligation

    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
     Coff
    -0.08
     Cain
    -0.06
     Mellon
    -0.06
    ffects
    -0.06
    ä½Ļ
    -0.06
    zer
    -0.06
     Ng
    -0.06
    247
    -0.06
     cherished
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
     willing
    0.21
     who
    0.21
    who
    0.19
     aware
    0.18
     whom
    0.18
     unaware
    0.18
     obliged
    0.17
     interested
    0.17
    interested
    0.17
     tasked
    0.16
    Activations Density 0.792%

    No Known Activations