© 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. 10633
    Prev
    Next
    INDEX
    Explanations

    java utility imports

    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
    ALO
    -0.08
    /etc
    -0.07
    ì´ī
    -0.07
    ()):
    -0.07
    .runtime
    -0.07
    heimer
    -0.07
     nợ
    -0.07
    ä¸įåİĮ
    -0.07
    veen
    -0.07
    teni
    -0.06
    POSITIVE LOGITS
    å®ķ
    0.07
    ãģĭãĤĮ
    0.07
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    0.06
    tl
    0.06
    çĴŁ
    0.06
    ;
    0.06
    ä¸įèĩªç¦ģ
    0.06
    å±ŀæĢ§åĴĮ
    0.06
    ä¹Łæ¯Ķ
    0.06
     as
    0.06
    Activations Density 0.297%

    No Known Activations