© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    variables, representing, potentials, spin, frame

    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
    æĿĢ伤
    -0.07
    umbang
    -0.07
    eness
    -0.06
    ç»ĻäºĪ
    -0.06
    äºı
    -0.06
    俱
    -0.06
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    -0.06
    è´¡çĮ®
    -0.06
    éĴ§
    -0.06
    roh
    -0.06
    POSITIVE LOGITS
    åıĺéĩı
    0.11
     variables
    0.10
     Variables
    0.10
    variables
    0.09
    åıĺéĩıçļĦ
    0.09
     ë³ĢìĪĺ
    0.09
    Variables
    0.09
    :variables
    0.08
     пеÑĢемен
    0.08
     representing
    0.08
    Activations Density 0.025%

    No Known Activations