© 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. 30334
    Prev
    Next
    INDEX
    Explanations

    concessions or contrasts

    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
    èį¡æ¼¾
    -0.07
    ãģĤãģŁ
    -0.07
    uesa
    -0.07
    нин
    -0.07
    ago
    -0.07
    çķ
    -0.07
    avian
    -0.06
     :(
    -0.06
    å±ĢéĿ¢
    -0.06
    avs
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.12
    åĽºçĦ¶
    0.11
    ä½Ĩä¹Łæľī
    0.11
    確ãģĭãģ«
    0.10
    —but
    0.10
    ä¹Łå¾Īéĩįè¦ģ
    0.10
    ç¡®å®ŀ
    0.10
    ãĤĤãģĤãĤĬãģ¾ãģĻãģĮ
    0.10
    ä½Ĩè¿Ļ
    0.10
    ,but
    0.10
    Activations Density 0.110%

    No Known Activations