© 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. 88932
    Prev
    Next
    INDEX
    Explanations

    climb, climbing, crawl

    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
     unfair
    -0.09
     whisk
    -0.09
    Cond
    -0.09
     shaved
    -0.08
     downloaded
    -0.08
     defer
    -0.08
    /functions
    -0.08
    757
    -0.08
     outr
    -0.08
     calculations
    -0.08
    POSITIVE LOGITS
     ladder
    0.16
     onto
    0.12
     climb
    0.12
     Clim
    0.12
     Craw
    0.12
     climbs
    0.11
     crawl
    0.11
    Bron
    0.11
    onto
    0.11
     climbing
    0.11
    Activations Density 0.019%

    No Known Activations