© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    AlxGa1-xN or AsxSe1-x</div>

    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
     Wolfe
    -0.07
    çķĮ
    -0.07
    iras
    -0.06
    olino
    -0.06
     object
    -0.06
     patterns
    -0.06
    ä¸ĭåįĪ
    -0.06
    object
    -0.06
    è¡ĮèĢħ
    -0.06
    éĺµ
    -0.06
    POSITIVE LOGITS
     unheard
    0.09
    è¾»
    0.08
    tock
    0.08
    åħ¶é¤ĺ
    0.08
    åħ¶ä½Ļ
    0.07
    msp
    0.07
    åIJ¸è¡Ģ
    0.07
    Tro
    0.07
    rest
    0.07
    reste
    0.07
    Activations Density 0.026%

    No Known Activations