© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    vulnerability, security, revenue, behavior

    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
    hiba
    -0.09
    afir
    -0.08
    å¼ıåĴĮ
    -0.08
    ardon
    -0.08
    ÃŃguez
    -0.08
    pile
    -0.08
    AREN
    -0.07
    _svc
    -0.07
    ìĥī
    -0.07
    (changes
    -0.07
    POSITIVE LOGITS
    iest
    0.07
    -enh
    0.07
    imid
    0.07
    濯
    0.07
    ائص
    0.06
     dÃŃky
    0.06
    æŃ£åĽłä¸º
    0.06
    èµ·è§ģ
    0.06
    ilen
    0.06
    лек
    0.06
    Activations Density 0.242%

    No Known Activations