© 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. 27797
    Prev
    Next
    INDEX
    Explanations

    sensitive state

    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
    ioneer
    -0.08
    airo
    -0.07
    çļĦçī¹èī²
    -0.07
    lend
    -0.07
    åĸ½
    -0.07
    _UNS
    -0.07
     Ponte
    -0.07
     Damas
    -0.07
    çī¹èī²
    -0.07
    à¸Ľà¸±à¸įà¸įา
    -0.07
    POSITIVE LOGITS
     sensitivity
    0.12
    æķıæĦŁåº¦
    0.12
     sensit
    0.11
    æķıæĦŁæĢ§
    0.09
    æķıæĦŁ
    0.09
    æķı
    0.09
    çģµæķı度
    0.09
    ensitivity
    0.08
     elasticity
    0.08
     nhạy
    0.08
    Activations Density 0.004%

    No Known Activations