© 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. 17809
    Prev
    Next
    INDEX
    Explanations

    shortest path

    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
    éĻ¤éĿŀ
    -0.07
    躲
    -0.07
    endon
    -0.07
     Unless
    -0.07
    ton
    -0.07
    MT
    -0.07
     unless
    -0.07
    áh
    -0.06
    åĨµä¸Ķ
    -0.06
    %(
    -0.06
    POSITIVE LOGITS
    æį¢åı¥è¯Ŀ说
    0.13
    ä¹Łå°±æĺ¯è¯´
    0.10
    æį¢è¨Ģä¹ĭ
    0.10
    è¿ĻæĦıåij³çĿĢ
    0.09
    åį³åľ¨
    0.09
    ooke
    0.08
    æĪĸèĢħ说
    0.08
     implies
    0.08
    åį³åĪ°
    0.08
    æĦıåij³çĿĢ
    0.08
    Activations Density 0.004%

    No Known Activations