© 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. 21672
    Prev
    Next
    INDEX
    Explanations

    Dialogue prefixes

    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
    缨
    -0.06
    åĵŁ
    -0.06
     방침
    -0.06
    çĶŁäºİ
    -0.06
    å§ĭç»Ī以
    -0.06
    éĩįè¦ģ讲è¯Ŀ
    -0.05
    湯
    -0.05
    Å¡in
    -0.05
    ij
    -0.05
     Lever
    -0.05
    POSITIVE LOGITS
    éģ¿
    0.06
     Rooney
    0.06
     geng
    0.06
    ptic
    0.06
    ffi
    0.06
    æİ
    0.06
    O
    0.05
    noch
    0.05
    奥
    0.05
    acara
    0.05
    Activations Density 0.002%

    No Known Activations