© 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. 47108
    Prev
    Next
    INDEX
    Explanations

    harboring, harbour, harbor Club, Harbor Grace

    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
    tle
    -0.08
    iated
    -0.08
    eka
    -0.08
    iad
    -0.08
    antz
    -0.07
     clad
    -0.07
     verbal
    -0.07
    iate
    -0.07
    enda
    -0.07
     drib
    -0.07
    POSITIVE LOGITS
     harb
    0.15
     harbour
    0.14
     resentment
    0.13
    ours
    0.13
     hidden
    0.12
    orage
    0.12
    ogn
    0.12
    ment
    0.12
     harbor
    0.12
    haft
    0.12
    Activations Density 0.003%

    No Known Activations