© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50321
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    elmi
    -0.09
    naver
    -0.08
     deteri
    -0.08
    lest
    -0.08
    Inh
    -0.08
    è½¬è½½çĽ®çļĦåľ¨äºİä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    -0.08
    qml
    -0.08
    ãĥ¼ãĥĦ
    -0.08
    _inds
    -0.07
    fillType
    -0.07
    POSITIVE LOGITS
    yc
    0.07
    代
    0.07
    çķª
    0.06
    ```
    0.06
    iks
    0.06
    å¡ŀ
    0.06
    in
    0.06
    ikian
    0.06
    é²ľ
    0.06
    åIJijå¾Ģ
    0.05
    Activations Density 0.193%

    No Known Activations