© 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. 114677
    Prev
    Next
    INDEX
    Explanations

    all, identical, equally

    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
    yer
    -0.10
     sometimes
    -0.10
     gust
    -0.10
    lama
    -0.09
    ãĥ©ãĥ³
    -0.09
     differently
    -0.09
     airs
    -0.09
    arna
    -0.09
    iken
    -0.09
     Sometimes
    -0.09
    POSITIVE LOGITS
     alike
    0.21
     necessarily
    0.16
     inherently
    0.15
     inevitably
    0.15
     equally
    0.14
     automatically
    0.14
     uniformly
    0.14
     universally
    0.13
     gleich
    0.13
     identical
    0.12
    Activations Density 0.202%

    No Known Activations