© 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. 24163
    Prev
    Next
    INDEX
    Explanations

    magazine and publication names

    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
    æī¿æİ¥
    -0.07
    éĻµ
    -0.06
    irat
    -0.06
     ÑĤÑı
    -0.06
    å©ī
    -0.06
    atering
    -0.06
    离
    -0.06
    åĮħåIJ«
    -0.06
    被
    -0.06
    æĺİæĺİ
    -0.06
    POSITIVE LOGITS
    åĪĺå¿Ĺ
    0.08
    ä¹ĭéĢī
    0.08
    æĿĤå¿Ĺ
    0.08
    å¤§ä½ľæĪĺ
    0.08
    lobal
    0.07
     wireType
    0.07
    æĹĹä¸ĭçļĦ
    0.07
    ucid
    0.07
    æĬ¡
    0.07
    çŃīå¤ļ家
    0.07
    Activations Density 0.392%

    No Known Activations