© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39374
    Prev
    Next
    INDEX
    Explanations

    cover up / hide / conceal

    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
    çĹ©
    -0.08
    çİ®
    -0.07
    mere
    -0.07
    нови
    -0.07
     vX
    -0.07
     revital
    -0.07
     Zak
    -0.06
    ereotype
    -0.06
    à¸į
    -0.06
     RequestMethod
    -0.06
    POSITIVE LOGITS
    æİ©çĽĸ
    0.15
    æݩ饰
    0.15
     conceal
    0.14
     hides
    0.14
    éļIJçŀĴ
    0.14
     hiding
    0.14
    åĽŀéģ¿
    0.12
     hide
    0.12
    éģ®æİ©
    0.12
     Hide
    0.12
    Activations Density 0.171%

    No Known Activations