© 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. 19219
    Prev
    Next
    INDEX
    Explanations

    control flow graph CFG

    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
    iono
    -0.06
    znál
    -0.06
    éĻĪè¿°
    -0.05
     respek
    -0.05
    Convention
    -0.05
    éĢIJå¹´
    -0.05
    agrams
    -0.05
    æĶ¾åľ¨å¿ĥä¸Ĭ
    -0.05
    èĦı
    -0.05
     Convention
    -0.05
    POSITIVE LOGITS
     mot
    0.07
     Folg
    0.05
    ãĥĸãĥ©ãĤ¦
    0.05
    طرة
    0.05
    åı¸
    0.05
    mot
    0.05
     ahead
    0.05
    ç¥Ģ
    0.05
    ppet
    0.05
    çŃīä¼ģä¸ļ
    0.05
    Activations Density 0.003%

    No Known Activations