© 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. 28229
    Prev
    Next
    INDEX
    Explanations

    lock and unlock

    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
     leaps
    -0.10
    olini
    -0.09
    coverage
    -0.09
    ogi
    -0.08
    izen
    -0.08
    ivi
    -0.08
     bare
    -0.08
     tent
    -0.08
     rud
    -0.08
     Spect
    -0.08
    POSITIVE LOGITS
    .Lock
    0.23
    unlock
    0.21
    (lock
    0.20
    .lock
    0.20
     Lock
    0.20
     unlocked
    0.20
     LOCK
    0.18
    LOCK
    0.18
     unlock
    0.18
    Lock
    0.18
    Activations Density 0.106%

    No Known Activations