© 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. 42284
    Prev
    Next
    INDEX
    Explanations

    why it matters

    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
    ãģ®ãģ§ãģĹãĤĩãģĨãģĭ
    -0.09
    çļĦåIJĹ
    -0.08
    ãģ®ãģłãĤįãģĨãģĭ
    -0.08
    åĵªä¸Ģ个
    -0.08
     whichever
    -0.08
    åIJĹ
    -0.08
     whatever
    -0.07
    åĹİ
    -0.07
    ëħIJ
    -0.07
    请éĹ®
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.09
    "":
    0.08
     |:
    0.08
    cent
    0.07
    ä»
    0.07
    è¿ĶåĽŀé¦ĸ页
    0.07
    )):
    0.07
    uckle
    0.07
    åıĬåħ¶å®ĥ
    0.07
     оÑĤли
    0.07
    Activations Density 0.187%

    No Known Activations