© 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. 25590
    Prev
    Next
    INDEX
    Explanations

    function definition list

    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
    omy
    -0.08
    æĸ¤
    -0.07
    oint
    -0.06
    Native
    -0.06
    åĸ§
    -0.06
     osc
    -0.06
    åıĮæĸ¹
    -0.06
    ر
    -0.06
    r
    -0.06
    åıªè¦ģä¸Ģ
    -0.06
    POSITIVE LOGITS
    æī¹éĩı
    0.13
     batch
    0.12
    æī¹æ¬¡
    0.11
    群ä½ĵ
    0.11
    群ä½ĵçļĦ
    0.11
    batch
    0.11
    éĽĨä½ĵçļĦ
    0.10
    éĽĨä½ĵ
    0.10
    绣ä¸Ģ管çIJĨ
    0.10
    æī¹
    0.10
    Activations Density 0.908%

    No Known Activations