© 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. 40767
    Prev
    Next
    INDEX
    Explanations

    chapter numbers and titles

    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
    éĹ´
    -0.07
    iet
    -0.07
    æĤī
    -0.07
    amil
    -0.07
    alon
    -0.07
    翻天
    -0.06
    ÑĢев
    -0.06
    andt
    -0.06
    æ·±å¤Ħ
    -0.06
     rel
    -0.06
    POSITIVE LOGITS
    æĽ´å¤ļ精彩
    0.07
    ç«łèĬĤ缮å½ķ
    0.07
     Stampa
    0.06
    åıĤåĬłæ¯ĶèµĽ
    0.06
     Pekan
    0.06
    è¡
    0.06
    lesi
    0.06
    åħ¬å¹³
    0.06
     consolidate
    0.06
    Å¡Äį
    0.06
    Activations Density 0.002%

    No Known Activations