© 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. 24747
    Prev
    Next
    INDEX
    Explanations

    later events

    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
    說ä»Ģ麼
    -0.07
    olato
    -0.07
    çĽİçĦ¶
    -0.07
    ç§ĴéĴŁ
    -0.07
     جد
    -0.06
    ola
    -0.06
    å¿ĺæĢĢ
    -0.06
    kont
    -0.06
    _CHAR
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
    POSITIVE LOGITS
     later
    0.30
    later
    0.25
    åIJİæĿ¥
    0.24
     Later
    0.23
    Later
    0.22
     ÙĦاØŃÙĤ
    0.21
     später
    0.21
     eventually
    0.21
     afterwards
    0.21
     subsequently
    0.21
    Activations Density 0.312%

    No Known Activations