© 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. 113407
    Prev
    Next
    INDEX
    Explanations

    saying or stating

    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
    anes
    -0.11
    issan
    -0.10
    iss
    -0.10
     Nicholson
    -0.10
    terminated
    -0.10
     Progressive
    -0.10
     ctl
    -0.10
     woll
    -0.10
    stands
    -0.09
     Ara
    -0.09
    POSITIVE LOGITS
     Rog
    0.08
     muttered
    0.08
     Franc
    0.08
     repeatedly
    0.08
    Repeated
    0.08
     simply
    0.08
    aza
    0.07
     crypt
    0.07
     Fault
    0.07
    edin
    0.07
    Activations Density 0.033%

    No Known Activations