© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17666
    Prev
    Next
    INDEX
    Explanations

    major concepts and components

    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
     sebel
    -0.06
     partly
    -0.06
    ihan
    -0.06
    åľ°ä½į
    -0.05
    wed
    -0.05
    åľ°ä½įçļĦ
    -0.05
    ạng
    -0.05
    é£İèµ·
    -0.05
    ä¸įåıª
    -0.05
    åıijæĮ¥
    -0.05
    POSITIVE LOGITS
    icule
    0.06
    ings
    0.06
    å°±åı¯ä»¥äºĨ
    0.06
    å¼Ħå¾Ĺ
    0.06
    áĥĵáĥĶ
    0.05
    çIJµ
    0.05
    ips
    0.05
    å°ıèħ¿
    0.05
    é¢ĸ
    0.05
    udur
    0.05
    Activations Density 0.012%

    No Known Activations