© 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. 89646
    Prev
    Next
    INDEX
    Explanations

    delight/delighted

    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
     likelihood
    -0.10
    shaw
    -0.10
    imos
    -0.10
     Buddy
    -0.10
     deb
    -0.09
     daylight
    -0.09
     Wich
    -0.09
    ulas
    -0.09
    dn
    -0.09
    ses
    -0.09
    POSITIVE LOGITS
    fully
    0.24
    ful
    0.19
    edly
    0.17
    enment
    0.16
    fulness
    0.15
    FUL
    0.14
    ously
    0.14
    ting
    0.11
    ingly
    0.11
    antly
    0.11
    Activations Density 0.004%

    No Known Activations