© 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. 90689
    Prev
    Next
    INDEX
    Explanations

    cruel paradox, tale, world

    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
     Trouble
    -0.11
     trouble
    -0.10
     irritating
    -0.09
     troublesome
    -0.09
     dang
    -0.09
     pes
    -0.09
    icha
    -0.09
    aran
    -0.08
     infuri
    -0.08
     uneasy
    -0.08
    POSITIVE LOGITS
     merciless
    0.21
     cruel
    0.21
     harsh
    0.20
     ruthless
    0.17
     cruelty
    0.17
     brutal
    0.16
     ruth
    0.16
     winters
    0.15
     Cru
    0.15
     punishments
    0.15
    Activations Density 0.047%

    No Known Activations