© 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. 17161
    Prev
    Next
    INDEX
    Explanations

    " , " followed by code keywords

    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
    带头
    -0.06
    éļ¾åº¦å¤§
    -0.05
    пиÑĤа
    -0.05
    绯
    -0.05
    åĪ°ä½İ
    -0.05
    пода
    -0.05
     Con
    -0.05
    'h
    -0.04
    zcz
    -0.04
    æķĪçİĩé«ĺ
    -0.04
    POSITIVE LOGITS
     perspectiv
    0.07
    eker
    0.06
    ation
    0.06
    ิà¹Īà¸ĩ
    0.06
    ances
    0.06
    izin
    0.06
    ancy
    0.06
    omin
    0.06
    oming
    0.06
    éĺ¿æĭī伯
    0.06
    Activations Density 0.013%

    No Known Activations