© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115876
    Prev
    Next
    INDEX
    Explanations

    interpreting ambiguous observations

    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
     secrets
    -0.10
     cá
    -0.09
     condemned
    -0.09
    ãĢİ
    -0.09
     dele
    -0.09
     perpet
    -0.09
     nam
    -0.09
     AVL
    -0.09
     preferred
    -0.09
     demanded
    -0.09
    POSITIVE LOGITS
     ambiguous
    0.18
     innoc
    0.14
     observed
    0.14
     situation
    0.13
     observations
    0.13
     ambigu
    0.12
     signals
    0.12
     scant
    0.12
     incomplete
    0.12
     symptoms
    0.12
    Activations Density 0.433%

    No Known Activations