© 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. 90236
    Prev
    Next
    INDEX
    Explanations

    vacation, resorts, camping, travel

    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
     street
    -0.13
     Theatre
    -0.12
    urai
    -0.11
     theat
    -0.11
     Metropolitan
    -0.11
    Opera
    -0.11
     Produ
    -0.11
     tonight
    -0.11
     café
    -0.11
     subst
    -0.11
    POSITIVE LOGITS
     vacation
    0.31
     vacations
    0.27
     Vacation
    0.25
     resorts
    0.23
     itinerary
    0.22
     honeymoon
    0.21
     camping
    0.20
     resort
    0.19
     Resorts
    0.19
     cabins
    0.19
    Activations Density 0.228%

    No Known Activations