© 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. 23694
    Prev
    Next
    INDEX
    Explanations

    if not, already not, if exists

    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
    -peer
    -0.07
    DefaultValue
    -0.07
    locales
    -0.07
    ä¹Łä¼ļæľī
    -0.07
    å¿ĥåľ°
    -0.07
    æĪªæŃ¢çĽ®åīį
    -0.07
    ä¸Ģ代
    -0.07
     Satz
    -0.07
     Pap
    -0.07
    软件ä¸ĭè½½
    -0.07
    POSITIVE LOGITS
     >=
    0.08
     detected
    0.07
    éĿŀè¦ģ
    0.07
    æ£ĢæµĭåĪ°
    0.07
     <=
    0.07
    åĪĨåĩº
    0.07
    å¤Ł
    0.07
    éĿŀ
    0.07
    å°ijäºİ
    0.07
    æľ¬ç¤¾
    0.07
    Activations Density 0.247%

    No Known Activations