© 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. 16267
    Prev
    Next
    INDEX
    Explanations

    field method or variables

    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
    /english
    -0.07
    ordinal
    -0.07
    æ¶īåıĬåĪ°
    -0.06
    unter
    -0.06
    apati
    -0.06
     concor
    -0.06
    สัà¸Ļ
    -0.06
    æ±Ĺ
    -0.06
    éł
    -0.06
     Shr
    -0.06
    POSITIVE LOGITS
    ä¸įè§ī
    0.09
     fields
    0.08
    åľºçļĦ
    0.08
    åĪļä¸Ģ
    0.07
     Fields
    0.07
    åľºå¤ĸ
    0.07
    åĬłçłģ
    0.07
    åĪļ
    0.07
     disemb
    0.07
    wijk
    0.07
    Activations Density 0.001%

    No Known Activations