© 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. 40282
    Prev
    Next
    INDEX
    Explanations

    end of sentences

    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
    åĿļ
    -0.08
    ä¸įéĹ®
    -0.07
    tida
    -0.06
    缪
    -0.06
    /jav
    -0.06
    resher
    -0.06
    åķ¸
    -0.06
     thro
    -0.06
    -animate
    -0.06
    /story
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.16
    è¿Ļ两个
    0.12
    è¿ĻäºĽéĥ½
    0.11
    è¿Ļ两
    0.11
    è¿Ļ两ç§į
    0.11
    è¿Ļ两款
    0.11
    ãģ©ãģ¡ãĤīãĤĤ
    0.11
    these
    0.11
    è¿Ļ两ä½į
    0.10
    ä½Ĩè¿ĻäºĽ
    0.10
    Activations Density 0.183%

    No Known Activations