© 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. 18691
    Prev
    Next
    INDEX
    Explanations

    mid-of-

    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
     manip
    -0.06
     fundamentally
    -0.05
    ysics
    -0.05
     meny
    -0.05
    ÑĥÑģ
    -0.05
    å¤Ħ
    -0.05
    ris
    -0.05
    resh
    -0.05
     inherently
    -0.05
    oure
    -0.05
    POSITIVE LOGITS
     pomóc
    0.06
     رÙĪاÙĨ
    0.06
     Gentle
    0.06
    aben
    0.06
     Deport
    0.06
    bÃŃ
    0.06
     richten
    0.06
    æīĺè¿IJ
    0.06
    ä¸ĢäºĽå°ı
    0.06
    iben
    0.05
    Activations Density 0.006%

    No Known Activations