© 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. 28286
    Prev
    Next
    INDEX
    Explanations

    imperative verbs

    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
    rios
    -0.12
     chalk
    -0.11
    ÙĪد
    -0.10
     ãĥ»
    -0.10
     Father
    -0.10
     repro
    -0.10
     Dro
    -0.10
     chuck
    -0.10
     Bamboo
    -0.10
    atie
    -0.10
    POSITIVE LOGITS
    !↵↵↵↵↵↵
    0.11
     Hur
    0.10
    !↵
    0.10
    !↵↵
    0.10
    ï¼ģ↵↵
    0.10
     brav
    0.10
    !.↵↵
    0.10
     !↵↵
    0.09
    endor
    0.09
     descr
    0.09
    Activations Density 0.111%

    No Known Activations