© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23767
    Prev
    Next
    INDEX
    Explanations

    foreign language or satisfy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onné
    -0.08
    æĦıå¤ĸçļĦ
    -0.08
    stantiate
    -0.08
    è¡
    -0.07
    ç½®ä¹ĭ
    -0.07
    å²Ĥ
    -0.07
    åĽ¾åºĵ
    -0.07
    fällig
    -0.07
    laut
    -0.07
    rug
    -0.07
    POSITIVE LOGITS
    èĥ½ä½¿
    0.10
     بØŃÙĬØ«
    0.10
    æĺ¯èĥ½
    0.10
    使å¾Ĺ
    0.09
    以使
    0.08
    æĺ¯æł¹æį®
    0.08
    满足
    0.08
    èĥ½è®©
    0.08
    èĥ½å¤Łä½¿
    0.08
     satisfy
    0.08
    Activations Density 0.161%

    No Known Activations