© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20983
    Prev
    Next
    INDEX
    Explanations

    light properties and phenomena

    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
    ed
    -0.06
    ierungs
    -0.05
    åı¯è¨Ģ
    -0.05
    éļĨ
    -0.05
    æ´¼
    -0.05
     Loc
    -0.05
     vice
    -0.05
    cor
    -0.05
    Raw
    -0.05
    apa
    -0.05
    POSITIVE LOGITS
    elight
    0.07
    bout
    0.06
    iems
    0.06
    avelength
    0.06
    asel
    0.06
    -election
    0.06
    鼷å°Ħ
    0.06
    交èŃ¦å¤§éĺŁ
    0.06
    Ø«ÙĨ
    0.06
    ows
    0.06
    Activations Density 0.025%

    No Known Activations