© 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. 20191
    Prev
    Next
    INDEX
    Explanations

    Let

    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
     بارد
    -0.07
    emm
    -0.07
    ç¡®æĿĥ
    -0.06
     عÙħراÙĨ
    -0.06
     اÙĦإد
    -0.06
    å°ģæݧ
    -0.06
    ØŃÙħÙĦ
    -0.06
    ected
    -0.06
    IfExists
    -0.06
    icio
    -0.06
    POSITIVE LOGITS
    pen
    0.06
    ä¾ĥ
    0.06
    eli
    0.06
     penetration
    0.05
    室åĨħå¤ĸ
    0.05
     fun
    0.05
     nom
    0.05
    ä»»
    0.05
     nonetheless
    0.05
    sequ
    0.05
    Activations Density 0.001%

    No Known Activations