© 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. 25046
    Prev
    Next
    INDEX
    Explanations

    `bin`, `.dart`, `Exception`

    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
     bet
    -0.06
    çĨŁæĤīçļĦ
    -0.06
    ¥
    -0.06
    ter
    -0.05
    èĻ½çĦ¶åľ¨
    -0.05
    ↵
    -0.05
     виÑģ
    -0.05
    ãģij
    -0.05
    åį³ä½¿åľ¨
    -0.05
    amm
    -0.05
    POSITIVE LOGITS
    æ³ĽæĮĩ
    0.15
    广ä¹ī
    0.13
    overall
    0.13
     encompasses
    0.13
     overall
    0.12
     generic
    0.12
     unspecified
    0.12
    åħ¨èĪ¬
    0.11
     broader
    0.11
    çļĦæķ´ä½ĵ
    0.11
    Activations Density 0.020%

    No Known Activations