© 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. 17587
    Prev
    Next
    INDEX
    Explanations

    snap, application, PPA, portable, store, package

    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
    åĤĻ
    -0.06
    ÑĢаÑĤ
    -0.06
     поÑģл
    -0.06
    èªĵ
    -0.06
    å¤ĩ
    -0.05
     asleep
    -0.05
    оÑĤа
    -0.05
    quete
    -0.05
    æ¸ħéĨĴ
    -0.05
    带好
    -0.05
    POSITIVE LOGITS
    è¿IJ
    0.07
     scale
    0.06
    æł¼
    0.06
    ley
    0.06
    款
    0.05
    hes
    0.05
    legate
    0.05
     (âĢ¦)
    0.05
     (...)
    0.05
    ENSIONS
    0.05
    Activations Density 0.002%

    No Known Activations