© 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. 32516
    Prev
    Next
    INDEX
    Explanations

    references or citations like [1]

    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
    åįģåŃĹ
    -0.08
    çł
    -0.07
    éħİ
    -0.07
    ider
    -0.06
     harmless
    -0.06
    akh
    -0.06
     Selle
    -0.06
     punch
    -0.06
    erot
    -0.06
     Goose
    -0.06
    POSITIVE LOGITS
    ilarity
    0.08
    owl
    0.08
    çĦ¶å¤§
    0.08
    istr
    0.08
    ily
    0.07
    åľ¨çº¿éĺħ读
    0.07
    Tpl
    0.07
    apy
    0.07
    WithValue
    0.07
    ä¸ĢçŃ¹
    0.07
    Activations Density 0.032%

    No Known Activations