© 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. 21865
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    ela
    -0.06
     Relevant
    -0.06
    zi
    -0.06
    åĬłä¹ĭ
    -0.05
    å¦ĤæĦı
    -0.05
    å°¤åħ¶æĺ¯
    -0.05
    relevant
    -0.05
    å°¤åħ¶æĺ¯åľ¨
    -0.05
    åħ³æ³¨åĴĮ
    -0.05
     tovább
    -0.05
    POSITIVE LOGITS
    éķľå¤´éĩĮ
    0.06
    cke
    0.06
    ÑģÑĤан
    0.06
    iste
    0.06
    .connector
    0.06
     explic
    0.06
    æĭŃ
    0.06
    åĬ¡
    0.06
     kali
    0.05
    ãģĹãģĭãģ£ãģŁãģ§ãģĻ
    0.05
    Activations Density 0.006%

    No Known Activations