© 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. 18024
    Prev
    Next
    INDEX
    Explanations

    solo piano, exhibit, artist, cup

    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
    ollo
    -0.10
    ات
    -0.08
    als
    -0.08
    issant
    -0.08
    icum
    -0.08
     clock
    -0.08
    ivers
    -0.08
    éli
    -0.08
     Christie
    -0.08
    oras
    -0.08
    POSITIVE LOGITS
     Solo
    0.12
    Solo
    0.11
    /group
    0.11
     traveler
    0.11
    travel
    0.11
     traveller
    0.11
     solo
    0.10
    Travel
    0.10
    -authored
    0.10
     Sik
    0.10
    Activations Density 0.013%

    No Known Activations