© 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. 14214
    Prev
    Next
    INDEX
    Explanations

    contends

    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
     aforementioned
    -0.10
    âĤ¬“
    -0.09
    credi
    -0.09
    gern
    -0.09
    urah
    -0.08
    úa
    -0.08
    emui
    -0.08
    обÑĢази
    -0.08
    urna
    -0.08
    æĸ¯åį¡
    -0.08
    POSITIVE LOGITS
     trim
    0.07
    ↵
    0.06
    âĢ
    0.06
    âĢIJ
    0.06
    ³
    0.06
    æĨ¬
    0.06
      ↵
    0.06
    ä¸ĩå¤ļåħĥ
    0.06
    —
    0.06
    ¹
    0.06
    Activations Density 0.071%

    No Known Activations