© 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. 8382
    Prev
    Next
    INDEX
    Explanations

    technical discussions or papers

    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
    urm
    -0.08
    ãģ¾ãģ¾ãģ§
    -0.07
    åħĭåĬĽ
    -0.07
    置顶
    -0.07
    çķ°
    -0.07
    _Copy
    -0.07
    æĶ¹éĢ²
    -0.07
    Mb
    -0.07
    è¬Ģ
    -0.07
    åħ¶æŀĹ
    -0.07
    POSITIVE LOGITS
     Interesting
    0.07
     interesting
    0.07
    azzi
    0.07
    é¡¹çĽ®æī¿åĬŀåįķä½į
    0.07
    ìĦ
    0.07
    ä»İè¿Ļ个
    0.07
     pointless
    0.06
    kot
    0.06
    çĭĻ
    0.06
    æĹłåħ³
    0.06
    Activations Density 0.047%

    No Known Activations