© 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. 18891
    Prev
    Next
    INDEX
    Explanations

    volume, brightness, and gain control

    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
    s
    -0.06
    qu
    -0.05
    å·¥æľŁ
    -0.05
     timing
    -0.05
    Timing
    -0.05
    åĴĮå½±åĵį
    -0.05
    å¤ļä¹ħ
    -0.05
    omin
    -0.05
    主导
    -0.05
    æŶéĹ´éķ¿
    -0.05
    POSITIVE LOGITS
    ento
    0.07
    ÙĨØ´
    0.06
    adder
    0.06
    mah
    0.06
    entar
    0.06
     dã
    0.06
    ENTO
    0.06
    alow
    0.06
     kapas
    0.06
    è§Ī
    0.06
    Activations Density 0.008%

    No Known Activations