© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    cause adverse effects

    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
    stype
    -0.06
    iedere
    -0.05
    åıijå±ķ模å¼ı
    -0.05
    人å¤ļ
    -0.05
    éĥ¨å°±
    -0.05
    ãĥĹãĥ¬ãĥ¼
    -0.05
    åĴĮç²¾ç¥ŀ
    -0.05
    çģ«èĬ±
    -0.05
    UTOR
    -0.05
     falsely
    -0.05
    POSITIVE LOGITS
     notions
    0.06
    oue
    0.06
    æ³Ľ
    0.06
    çĬ¹
    0.05
    åı¯èĥ½åĩºçİ°
    0.05
     belakang
    0.05
    åı¯èĥ½åŃĺåľ¨
    0.05
    èĢĥ
    0.05
    aff
    0.05
    åĨħ
    0.05
    Activations Density 0.006%

    No Known Activations