© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55080
    Prev
    Next
    INDEX
    Explanations

    lock, unlock, blocking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     salv
    -0.11
     lump
    -0.11
    -final
    -0.11
     Feed
    -0.10
    Feed
    -0.10
     feed
    -0.10
    /form
    -0.10
     frags
    -0.10
     final
    -0.10
     feeds
    -0.10
    POSITIVE LOGITS
     blocking
    0.10
     conflict
    0.09
     barrier
    0.08
     conflicts
    0.08
     inhib
    0.08
    REW
    0.08
     Blocking
    0.07
     blocker
    0.07
     locking
    0.07
     locks
    0.07
    Activations Density 0.030%

    No Known Activations