© 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. 17579
    Prev
    Next
    INDEX
    Explanations

    XML/HTML tags and code snippets

    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
    åĪĺ家
    -0.06
    chend
    -0.06
    eld
    -0.06
    æĹłæķĮ
    -0.06
    arian
    -0.06
    æľ¬åĵģ
    -0.06
    ä¸Ģ身
    -0.06
    EK
    -0.06
    ymbol
    -0.06
    ness
    -0.06
    POSITIVE LOGITS
    欲
    0.05
    åıijé»Ħ
    0.05
    æĢ§ä¸İ
    0.05
    åħ¸
    0.05
     Nur
    0.05
    ÙĤÙĬ
    0.05
    æĢ§éĹ®é¢ĺ
    0.05
    为ä»Ģä¹Ī
    0.05
    ÙĦس
    0.05
    plas
    0.05
    Activations Density 0.033%

    No Known Activations