© 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. 20491
    Prev
    Next
    INDEX
    Explanations

    predefined layouts

    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
    óst
    -0.09
    strup
    -0.08
    aksi
    -0.08
    áh
    -0.07
    ellt
    -0.07
     fucked
    -0.07
    çļĦ红
    -0.07
    övet
    -0.07
    еÑĢов
    -0.07
    èĥĮæĻ¯çļĦ
    -0.07
    POSITIVE LOGITS
    avar
    0.07
    å½ĵ家
    0.07
    wel
    0.07
     '
    0.06
    é´
    0.06
    /DD
    0.06
    æľīçļĦåIJĮåѦ
    0.06
      ↵    ↵
    0.06
    ebles
    0.06
     íĽ¼
    0.06
    Activations Density 0.001%

    No Known Activations