© 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. 32483
    Prev
    Next
    INDEX
    Explanations

    downward movement

    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
     climbing
    -0.15
     climbers
    -0.14
     climb
    -0.12
     climbs
    -0.12
     ladder
    -0.12
     lev
    -0.11
     bip
    -0.11
    stairs
    -0.10
     pedal
    -0.10
     stairs
    -0.10
    POSITIVE LOGITS
     plummet
    0.11
     hypers
    0.10
     jumping
    0.10
     jumped
    0.09
    elog
    0.09
     spreads
    0.09
     leap
    0.09
    lah
    0.09
     launched
    0.09
     Tow
    0.09
    Activations Density 0.067%

    No Known Activations