© 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. 19111
    Prev
    Next
    INDEX
    Explanations

    in turn, followed by 'requires' or 'depend'

    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
    akor
    -0.10
     ÙĨبا
    -0.08
    eret
    -0.08
    apor
    -0.07
    驾
    -0.07
    ä¹Łæĺ¯è¿Ļæł·
    -0.07
    ulah
    -0.07
     woll
    -0.07
    ngth
    -0.07
    é§ķ
    -0.07
    POSITIVE LOGITS
     wiederum
    0.12
    åıĪåı¯
    0.10
    åıĪå¤ļ
    0.09
    åıĪæľī
    0.09
    åıĪåľ¨
    0.09
    åıĪæĺ¯
    0.09
    åıĪ
    0.09
    åıĪ以
    0.08
    åıĪ被
    0.08
     zase
    0.08
    Activations Density 0.306%

    No Known Activations