© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 29988
    Prev
    Next
    INDEX
    Explanations

    geometry"> <rect> <x>0</x> <y>0</y> <width>attribute name="value"value="true"Value="public class CodeAttributeDeclarationCollection : System.Collections.CollectionBase" />value="some string"value = "a"value = 123Value is `true` or `false`

    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
    à¸¹à¸Ľ
    -0.07
    éĤĥ
    -0.07
    å®Ŀå±±
    -0.07
     
    -0.06
    è¹ĭ
    -0.06
    нÑİ
    -0.06
    ãģĭãģĴ
    -0.06
    arus
    -0.06
      
    -0.06
    <|box_end|>
    -0.06
    POSITIVE LOGITS
    <|repo_name|>
    0.07
    Ïħνα
    0.07
    çĪĨåĩº
    0.07
    ç½
    0.07
     Detalles
    0.07
    éĽ
    0.06
    ministr
    0.06
    æľīè¾ĥ强çļĦ
    0.06
    "group
    0.06
    emas
    0.06
    Activations Density 0.008%

    No Known Activations