© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19026
    Prev
    Next
    INDEX
    Explanations

    “I’m” or “how”

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iket
    -0.07
    ossal
    -0.06
    Äįit
    -0.06
    upun
    -0.05
    æ´»
    -0.05
    è¯¥æľº
    -0.05
    个头
    -0.05
    entrer
    -0.05
    åĴĨåĵ®
    -0.05
    ikin
    -0.05
    POSITIVE LOGITS
    ä¹ħä¹ĭ
    0.07
    为éļ¾
    0.06
     proxy
    0.06
    åįĬ天
    0.06
     proxies
    0.06
    太ä¹ħ
    0.06
    tas
    0.06
    éĹ´æİ¥
    0.06
     indirectly
    0.06
     parity
    0.06
    Activations Density 0.008%

    No Known Activations