© 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. 20385
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    urgo
    -0.08
    orando
    -0.08
    ä½Ĩæĺ¯è¿Ļ
    -0.08
    ulia
    -0.08
    angler
    -0.07
    åĽłæĤ¨çļĦ
    -0.07
    åľ¨æľ¬ç«Ļ
    -0.07
    edList
    -0.07
    ä¸į缺
    -0.07
    å°¤
    -0.07
    POSITIVE LOGITS
     lands
    0.06
    çŃĶé¢ĺåį¡
    0.06
    emat
    0.06
    Ùģاء
    0.06
     laver
    0.06
    esi
    0.06
     endorsement
    0.06
    åľ°è¯´
    0.06
    éĽªçIJĥ
    0.06
    ssi
    0.06
    Activations Density 0.028%

    No Known Activations