© 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. 63144
    Prev
    Next
    INDEX
    Explanations

    penetration depth

    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
    éļıçĿĢæŶéĹ´çļĦ
    -0.07
    ä½ľæģ¯æŶéĹ´
    -0.07
    ench
    -0.07
    shake
    -0.07
    åīªåĪĢ
    -0.07
    Č↵
    -0.07
     пÑĢиÑĩ
    -0.07
     ÑĢано
    -0.07
    framework
    -0.07
    robots
    -0.07
    POSITIVE LOGITS
    ç©¿éĢı
    0.11
     penetrating
    0.08
     penetr
    0.08
     penetration
    0.08
     transmis
    0.08
    ç©¿è¿ĩ
    0.08
    à¸Ĺะ
    0.07
     penetrate
    0.07
     пÑĢоника
    0.07
     transmission
    0.07
    Activations Density 0.012%

    No Known Activations