© 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. 31846
    Prev
    Next
    INDEX
    Explanations

    Wayne followed by names or places

    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
     Dum
    -0.10
    Americ
    -0.08
    otti
    -0.08
    orsch
    -0.08
     pou
    -0.08
    urch
    -0.07
     po
    -0.07
    sembles
    -0.07
     Bath
    -0.07
     Donovan
    -0.07
    POSITIVE LOGITS
     preceded
    0.12
    RestController
    0.12
    /send
    0.10
    elastic
    0.10
     Chan
    0.10
    eka
    0.10
    preced
    0.10
    ahead
    0.10
     Retro
    0.10
     TIM
    0.10
    Activations Density 0.002%

    No Known Activations