© 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. 33154
    Prev
    Next
    INDEX
    Explanations

    male/female aged 1-20 years

    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
    vider
    -0.09
    æĥ³å¾Ĺ
    -0.08
    alc
    -0.08
     indexOf
    -0.08
    AtIndex
    -0.08
    æķ¦
    -0.07
    æľīå¥ĸ
    -0.07
    erei
    -0.07
    uwen
    -0.07
    anzas
    -0.07
    POSITIVE LOGITS
    ilet
    0.07
    anges
    0.07
    ieger
    0.07
    auta
    0.06
    ÙĪÙĬات
    0.06
    วà¸ļ
    0.06
    åįłåħ¬åı¸
    0.06
    éļĪ
    0.06
    orent
    0.06
    _bag
    0.06
    Activations Density 0.100%

    No Known Activations