© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30546
    Prev
    Next
    INDEX
    Explanations

    apologize for writing

    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
    åĢŁæѤ
    -0.07
    Ù°
    -0.07
    ilos
    -0.06
     воз
    -0.06
    åŃĺ
    -0.06
    imid
    -0.06
     benefited
    -0.06
    undang
    -0.06
    æīįè¡Į
    -0.06
    (&_
    -0.06
    POSITIVE LOGITS
    å¦ĤæѤ
    0.10
    对ä¸Ģ个
    0.10
    è¿Ļä¹Ī大
    0.09
    è¿Ļä¹Ī
    0.09
    ä½łè¿Ļä¹Ī
    0.09
    ambu
    0.09
     ÚĨÙĨÛĮÙĨ
    0.09
    è¿ĶåĽŀ顶éĥ¨
    0.09
    æľīè¿Ļæł·çļĦ
    0.08
    å¦ĤæѤä¹ĭ
    0.08
    Activations Density 0.047%

    No Known Activations