© 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. 25754
    Prev
    Next
    INDEX
    Explanations

    camping and scouting activities

    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
     Streets
    -0.13
     streets
    -0.12
     Bahrain
    -0.11
     street
    -0.11
     elevator
    -0.11
     sweeps
    -0.10
     Fet
    -0.10
     swept
    -0.09
     upstairs
    -0.09
     sweep
    -0.09
    POSITIVE LOGITS
     camping
    0.49
     camp
    0.46
     campground
    0.44
     camper
    0.43
     Camping
    0.43
     Camp
    0.38
     camps
    0.37
    camp
    0.34
    Camp
    0.34
     tents
    0.33
    Activations Density 0.300%

    No Known Activations