© 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. 1106
    Prev
    Next
    INDEX
    Explanations

    needs, norms, style, preferences

    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
    ÑĩÑĭ
    -0.08
    æī©å¤§åĪ°
    -0.07
    Included
    -0.07
     pina
    -0.07
    kish
    -0.07
     Included
    -0.07
    landa
    -0.07
    çļĦèĥĮåIJİ
    -0.07
    ÃŃnh
    -0.06
    ä¸Ģç³»åĪĹçļĦ
    -0.06
    POSITIVE LOGITS
    çī¹çĤ¹
    0.11
    å®ŀéĻħæĥħåĨµ
    0.11
    çī¹çĤ¹åĴĮ
    0.10
    åĽ½æĥħ
    0.10
    åĴĮ社ä¼ļåıijå±ķ
    0.10
     ÙĪاØŃت
    0.09
    å®ŀæĥħ
    0.09
    æī¬éķ¿
    0.09
     needs
    0.09
    çŃīçī¹çĤ¹
    0.09
    Activations Density 0.050%

    No Known Activations