© 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. 21379
    Prev
    Next
    INDEX
    Explanations

    code syntax: `key`, assignments, method calls

    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
    igente
    -0.06
    dok
    -0.06
    ÙĨاد
    -0.06
    ãģıãģłãģķãģĦãģŃ
    -0.06
     Posta
    -0.06
     proportion
    -0.06
    oge
    -0.06
    ment
    -0.06
    odate
    -0.06
     hent
    -0.06
    POSITIVE LOGITS
    å¼ĺ
    0.05
    åĮħ
    0.05
    éģ¿
    0.05
    å±ĭ
    0.05
    åı
    0.05
    èħ¹
    0.05
    AB
    0.05
    æķ
    0.05
     обÑģ
    0.05
    çŀŃ
    0.05
    Activations Density 0.002%

    No Known Activations