© 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. 27597
    Prev
    Next
    INDEX
    Explanations

    blindness or guessing

    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
     watching
    -0.15
     viewing
    -0.14
     Watching
    -0.13
     stare
    -0.13
     glance
    -0.13
     Viewing
    -0.13
     watched
    -0.13
     look
    -0.13
     Blick
    -0.13
     looks
    -0.12
    POSITIVE LOGITS
     blind
    0.22
     Blind
    0.19
     blindness
    0.17
    blind
    0.17
     blindly
    0.16
     guessing
    0.15
    -blind
    0.14
     guessed
    0.14
     blinded
    0.13
     unidentified
    0.13
    Activations Density 0.050%

    No Known Activations