© 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. 116829
    Prev
    Next
    INDEX
    Explanations

    climbing, rappelling, grip

    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
     tuning
    -0.10
     basement
    -0.09
     upstairs
    -0.09
    lid
    -0.09
     lid
    -0.08
     Reform
    -0.08
     Bron
    -0.08
     downstairs
    -0.08
    udo
    -0.08
     Tun
    -0.08
    POSITIVE LOGITS
     clinging
    0.21
     rapp
    0.18
     climbing
    0.18
     climbers
    0.17
     cling
    0.17
     gripping
    0.17
     grip
    0.16
     climb
    0.16
     dangling
    0.15
     crawling
    0.15
    Activations Density 0.163%

    No Known Activations