© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22302
    Prev
    Next
    INDEX
    Explanations

    Tag Archive, Category Archive

    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
    å¤ĸçķĮ
    -0.07
    Pres
    -0.06
     stored
    -0.05
    å®ŀéĻħæĥħåĨµ
    -0.05
    ehr
    -0.05
    å¤ĸçķĮçļĦ
    -0.05
    çļĦçݯå¢ĥä¸ĭ
    -0.05
     pres
    -0.05
     Pres
    -0.05
    åĬ¿åĬĽ
    -0.05
    POSITIVE LOGITS
    idden
    0.06
    å¹¿æ³Ľåħ³æ³¨
    0.05
    .INVISIBLE
    0.05
    åĪĨ为
    0.05
    ische
    0.05
    eme
    0.05
    ocomplete
    0.05
    æľīåı²
    0.05
    主è¦ģåĪĨ为
    0.05
    å¾Ĺè¿ĩ
    0.05
    Activations Density 0.003%

    No Known Activations