© 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. 48591
    Prev
    Next
    INDEX
    Explanations

    previous study

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    resa
    -0.07
    ãĤ¥
    -0.07
    tell
    -0.07
    PackageManager
    -0.06
    éķij
    -0.06
    ä¸Ģåı·
    -0.06
    çļĦéģĵçIJĨ
    -0.06
    åħµåĻ¨
    -0.06
    ä¸Ģæ¡£
    -0.06
    POSITIVE LOGITS
    åľ¨å¿ħ
    0.08
    imak
    0.08
    åĪĨæŀIJåıĬ
    0.07
     analogy
    0.07
    溪éķĩ
    0.07
    åĪĨæŀIJä¸İ
    0.07
    ר×ķף
    0.07
     analysis
    0.07
    Ñĩенко
    0.07
    ahan
    0.07
    Activations Density 0.008%

    No Known Activations