© 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. 23998
    Prev
    Next
    INDEX
    Explanations

    C++ function declarations

    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
    äºĭä¸ļçļĦ
    -0.07
    äºĭä¸ļ
    -0.07
    ungeon
    -0.06
    ichever
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    umper
    -0.06
     potr
    -0.06
    문íķĻ
    -0.06
    åģļçļĦå°±æĺ¯
    -0.06
    uname
    -0.06
    POSITIVE LOGITS
    *;
    0.08
    代人
    0.08
    以åıĬå¦Ĥä½ķ
    0.07
    боÑİ
    0.07
    SECTION
    0.07
    ستر
    0.07
    iaux
    0.07
    lau
    0.07
    åĴ«å°º
    0.07
    _STD
    0.07
    Activations Density 0.122%

    No Known Activations