© 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. 10521
    Prev
    Next
    INDEX
    Explanations

    learning, food, reproduction, pain, sleep

    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
    åİŁæ±ģ
    -0.08
    æŁĴ
    -0.08
    <Any
    -0.08
    丹丹
    -0.07
    _MAKE
    -0.07
    Deaths
    -0.07
    ajem
    -0.07
    ikian
    -0.07
     excer
    -0.07
    å¼łçħ§çīĩ
    -0.07
    POSITIVE LOGITS
    è°ĥæݧ
    0.08
    è´®
    0.07
    åħ·æľīéĩįè¦ģ
    0.07
    ä¸įåı¯æĪĸ缺
    0.07
    ocale
    0.07
     domains
    0.06
    ä¸įåı¯æĪĸ缺çļĦ
    0.06
    -related
    0.06
    æĭĽåĭŁ
    0.06
    è¿ĩ度çļĦ
    0.06
    Activations Density 0.630%

    No Known Activations