© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    foreign language and punctuation

    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
    åĽłä¸ºæ²¡æľī
    -0.08
     Afinal
    -0.08
    borne
    -0.07
    ublic
    -0.07
    urgo
    -0.07
    åıįæŃ£
    -0.07
    ourn
    -0.07
    jakan
    -0.07
    å¾ī
    -0.07
    éĻįåĪ°æľĢä½İ
    -0.07
    POSITIVE LOGITS
    æīĢ以å½ĵ
    0.12
    åĽłæŃ¤åľ¨
    0.11
    åĽłæѤ
    0.10
     donc
    0.10
    æīĢä»¥åľ¨
    0.09
     Therefore
    0.09
    Therefore
    0.09
     therefore
    0.09
    æīĢ以è¦ģ
    0.09
     поÑįÑĤомÑĥ
    0.09
    Activations Density 0.232%

    No Known Activations