© 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. 28717
    Prev
    Next
    INDEX
    Explanations

    wish or wishing for

    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
    iller
    -0.10
    elan
    -0.10
     ris
    -0.09
    gle
    -0.09
     warrant
    -0.09
    bast
    -0.09
     Bros
    -0.09
     Likely
    -0.09
    DAQ
    -0.08
     promise
    -0.08
    POSITIVE LOGITS
     wished
    0.19
     wish
    0.19
     wishes
    0.18
     someday
    0.18
     wishing
    0.17
    wish
    0.17
     Wish
    0.17
     ferv
    0.14
     hoping
    0.13
    hop
    0.13
    Activations Density 0.081%

    No Known Activations