© 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. 26997
    Prev
    Next
    INDEX
    Explanations

    puncutation and non-english words

    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
    æĥħåĨµåIJİ
    -0.07
    åľ¨ä¸Ĭè¿°
    -0.07
    å±ħçĦ¶æĺ¯
    -0.06
     qualc
    -0.06
     kho
    -0.06
    reis
    -0.06
    å®ĥéĤ£
    -0.06
    åħĭç½Ĺ
    -0.06
    _foreign
    -0.06
     admir
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľä¸Ģ个
    0.08
    éĢļ常
    0.08
     typically
    0.07
     trouble
    0.07
    çģ¿
    0.07
    à¸į
    0.07
    lesen
    0.07
     ThuáºŃn
    0.07
     often
    0.07
    ãģķãģ¦
    0.06
    Activations Density 0.083%

    No Known Activations