© 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. 48442
    Prev
    Next
    INDEX
    Explanations

    changes and transitions

    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
     penchant
    -0.07
    dera
    -0.07
    _TICK
    -0.07
    apr
    -0.07
    缴åĪ°çİ°åľ¨
    -0.06
    nock
    -0.06
    æĢĿæĥ³å·¥ä½ľ
    -0.06
    etry
    -0.06
    åİŁåĪĽæĸĩç«ł
    -0.06
    丽èIJį
    -0.06
    POSITIVE LOGITS
    æ´»åĬ¨æŶ
    0.14
    åıijçĶŁæŶ
    0.13
    éĹ®é¢ĺæŶ
    0.12
    éļıçĿĢ
    0.12
    ä½ľä¸ļæŶ
    0.11
    å·¥ä½ľæŶ
    0.11
    åľ¨è¿Ľåħ¥
    0.10
    æīĢ以å½ĵ
    0.10
    使çĶ¨æŶ
    0.10
    æĬ¥åIJįæŶ
    0.10
    Activations Density 0.164%

    No Known Activations