© 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. 49148
    Prev
    Next
    INDEX
    Explanations

    grouping symbols

    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
     neve
    -0.08
    åħ¨éĥ¨è´£ä»»
    -0.06
    hofer
    -0.06
    æĸ¹èĥ½
    -0.06
    ãģĤãģı
    -0.06
    è·¯éĢı
    -0.06
    ฯ
    -0.06
    IEW
    -0.06
     dite
    -0.06
    idor
    -0.06
    POSITIVE LOGITS
    erer
    0.08
    upy
    0.08
    UDI
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    两åѦä¸Ģåģļ
    0.07
    æĪĸå¤ļ个
    0.07
    upa
    0.07
    èĢģå°ij
    0.07
    å°¤
    0.07
    èv
    0.07
    Activations Density 0.014%

    No Known Activations