© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26102
    Prev
    Next
    INDEX
    Explanations

    locks and mutexes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    ignes
    -0.11
    被æ·ĺæ±°
    -0.07
    失èģĶ
    -0.07
    heus
    -0.07
    ipur
    -0.07
    vány
    -0.07
    æıļ
    -0.07
    ignant
    -0.07
    attes
    -0.07
    createCommand
    -0.07
    POSITIVE LOGITS
     access
    0.08
    æİĴ
    0.08
     mutex
    0.08
    çĭ¬åįł
    0.08
     blocking
    0.08
    éĺ²æŃ¢
    0.07
     lock
    0.07
    access
    0.07
    åħĪåĪ°åħĪå¾Ĺ
    0.07
     locks
    0.07
    Activations Density 0.069%

    No Known Activations