© 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. 20343
    Prev
    Next
    INDEX
    Explanations

    defined with typing

    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
    éĢIJ项
    -0.07
    ospel
    -0.06
    ellig
    -0.06
    ocz
    -0.06
    éģĤ
    -0.06
    _pub
    -0.06
    ä¹İ
    -0.06
    odel
    -0.06
     mith
    -0.06
     revend
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī为
    0.10
     defined
    0.10
     definitions
    0.10
    å®ļä¹ī
    0.09
    ä¸ľå±±
    0.08
     definition
    0.08
     dabei
    0.08
     Defined
    0.08
    çļĦå®ļä¹ī
    0.08
    å®ļä¹īäºĨ
    0.08
    Activations Density 0.011%

    No Known Activations