© 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. 60763
    Prev
    Next
    INDEX
    Explanations

    hidden, concealed, covert

    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
    opies
    -0.08
    ODE
    -0.08
    OTO
    -0.07
    å±ķæľĽæľªæĿ¥
    -0.07
    èݱæĸ¯
    -0.07
    å±ķæľĽ
    -0.07
    odom
    -0.07
    çĽ¸ä¿¡åľ¨
    -0.07
    èĤª
    -0.07
    eref
    -0.06
    POSITIVE LOGITS
     hidden
    0.23
    hidden
    0.21
     secretly
    0.21
    éļIJèĹı
    0.21
    éļIJèĶ½
    0.21
    éļIJç§ĺ
    0.20
     concealed
    0.20
     Hidden
    0.19
     covert
    0.19
    éļIJèĹıçļĦ
    0.19
    Activations Density 0.396%

    No Known Activations