© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    supposed to or tasked with

    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
    ebol
    -0.08
    бом
    -0.07
    缸éļı
    -0.07
     absentee
    -0.07
    itora
    -0.07
    ocz
    -0.07
    rb
    -0.07
    antd
    -0.07
    æ°¸è¿ľæĺ¯
    -0.07
    anzo
    -0.07
    POSITIVE LOGITS
    çļĦè¦ģæ±Ĥ
    0.14
    è¦ģæ±Ĥ
    0.14
    è¦ģæ±ĤçļĦ
    0.13
    è¦ģæ±Ĥåľ¨
    0.13
    è¦ģæ±Ĥèĩªå·±
    0.13
     requirement
    0.12
    æĺİç¡®è¦ģæ±Ĥ
    0.12
     requirements
    0.12
    åħ·ä½ĵè¦ģæ±Ĥ
    0.12
    æĮĩå®ļ
    0.12
    Activations Density 0.044%

    No Known Activations