© 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. 20358
    Prev
    Next
    INDEX
    Explanations

    procedural 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
     passeio
    -0.06
     arran
    -0.06
    å½ĵ代
    -0.06
    loc
    -0.06
    -Assad
    -0.06
    èĸ
    -0.06
    venge
    -0.06
     intimid
    -0.06
    ä¸Ĭéĺµ
    -0.06
    kk
    -0.06
    POSITIVE LOGITS
     maneuvers
    0.06
    rau
    0.05
    AB
    0.05
    æĬ¥æĸĩ
    0.05
    ìĸ´ë¡ľ
    0.05
    å±ı
    0.05
    æĮĩ令
    0.05
     radio
    0.05
     incoming
    0.05
     ADS
    0.05
    Activations Density 0.011%

    No Known Activations