© 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. 44054
    Prev
    Next
    INDEX
    Explanations

    'elle' followed by 'e'

    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
    æīij
    -0.08
    åĩŃèIJ¥ä¸ļæī§çħ§
    -0.08
    åħ¬åı¸æĪIJåijĺ
    -0.07
     permett
    -0.07
     Leaders
    -0.06
    arro
    -0.06
    lauben
    -0.06
    dings
    -0.06
    presso
    -0.06
    dcc
    -0.06
    POSITIVE LOGITS
     whom
    0.11
     who
    0.09
    è°ģæĺ¯
    0.09
    who
    0.08
    ä¸Ģæĸ¹
    0.08
    å¤ļæĸ¹
    0.08
     enjo
    0.07
    .defineProperty
    0.07
    åħ¼
    0.07
    chenk
    0.07
    Activations Density 0.385%

    No Known Activations