© 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. 3835
    Prev
    Next
    INDEX
    Explanations

    unlocking or unlocking codes

    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
    cot
    -0.10
    ól
    -0.10
    blr
    -0.10
     stal
    -0.09
    coin
    -0.09
     dilig
    -0.09
    Repair
    -0.09
    colo
    -0.09
     Cot
    -0.09
    etas
    -0.09
    POSITIVE LOGITS
     unlock
    0.15
     locked
    0.14
     unlocked
    0.14
     doors
    0.13
     unlocking
    0.12
     locks
    0.12
     unlocks
    0.11
     Doors
    0.10
     door
    0.10
    ables
    0.10
    Activations Density 0.033%

    No Known Activations