© 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. 15955
    Prev
    Next
    INDEX
    Explanations

    origin of testimony

    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
    请çĤ¹åĩ»
    -0.07
    åľŃ
    -0.07
    åĿĩçĶ±
    -0.07
    å®ĺæĸ¹å¾®ä¿¡
    -0.07
    ãĤµ
    -0.07
    ｡
    -0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    inke
    -0.06
    nik
    -0.06
     elkaar
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½ä¼ļ导èĩ´
    0.10
    æľīçĽĬäºİ
    0.09
     conducive
    0.09
    æľīåĬ©äºİ
    0.09
    åı¯èĥ½å¯¼èĩ´
    0.09
    缴æİ¥åħ³ç³»åĪ°
    0.09
    åĬ©äºİ
    0.09
     indirectly
    0.08
    _mono
    0.08
    ä¼ļå½±åĵį
    0.08
    Activations Density 0.003%

    No Known Activations