© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    after following token

    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
    yss
    -0.09
    aldi
    -0.07
    cek
    -0.07
    ä¸Ģ举
    -0.07
    unge
    -0.07
    Å¡tÄĽ
    -0.07
    engk
    -0.07
    rens
    -0.07
     Verz
    -0.07
    umper
    -0.07
    POSITIVE LOGITS
     nachdem
    0.08
    åĪ¨
    0.08
    æĹ¢çĦ¶
    0.08
    @d
    0.07
    æĹ¢çĦ¶æĺ¯
    0.07
    éĹ»
    0.07
     ìĥģíĻ©ìĹIJìĦľ
    0.07
    åŁºäºİ
    0.06
    身å¤Ħ
    0.06
    wi
    0.06
    Activations Density 0.037%

    No Known Activations