© 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. 48283
    Prev
    Next
    INDEX
    Explanations

    class constructors

    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
    æİī
    -0.07
    æĸŃç»Ń
    -0.07
    éĻĮ
    -0.07
    retto
    -0.07
    大åĬ¿
    -0.07
    лоне
    -0.07
    åĩºå±Ģ
    -0.07
    æİīçļĦ
    -0.07
    ancers
    -0.07
     Ansi
    -0.07
    POSITIVE LOGITS
     constructor
    0.12
    æŀĦéĢłåĩ½æķ°
    0.10
    constructor
    0.10
     Constructor
    0.09
    	constructor
    0.09
    _ctor
    0.09
     ctor
    0.08
     initWith
    0.08
    _constructor
    0.08
    åĪĿå§ĭåĮĸ
    0.08
    Activations Density 0.245%

    No Known Activations