© 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. 116440
    Prev
    Next
    INDEX
    Explanations

    wishes granted or fulfilled

    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
    assel
    -0.10
    sto
    -0.09
     gst
    -0.09
     Caucas
    -0.09
     reprodu
    -0.08
    jn
    -0.08
     Emmanuel
    -0.08
     Je
    -0.08
     Rice
    -0.08
     macros
    -0.08
    POSITIVE LOGITS
     granted
    0.22
     Granted
    0.17
     grant
    0.17
     granting
    0.17
     grants
    0.14
    Granted
    0.13
     honoring
    0.12
     fulfilled
    0.12
    grant
    0.12
     fulfillment
    0.12
    Activations Density 0.020%

    No Known Activations