© 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. 20303
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    åĪ°æľī
    -0.09
    unku
    -0.08
    ấm
    -0.08
    ЧÐIJ
    -0.08
    dden
    -0.08
    onti
    -0.08
    teroid
    -0.08
    okus
    -0.08
     Budd
    -0.08
    -errors
    -0.08
    POSITIVE LOGITS
    åĴĮèĩªå·±
    0.07
    åıĸéķ¿è¡¥çŁŃ
    0.07
    å»
    0.06
    ell
    0.06
     ken
    0.06
    ç»Ļ对æĸ¹
    0.06
     اÙĦبعض
    0.06
    åľ¨åIJĮä¸Ģ
    0.06
    TF
    0.06
    geg
    0.06
    Activations Density 0.109%

    No Known Activations