© 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. 20781
    Prev
    Next
    INDEX
    Explanations

    semiconductor materials

    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
    æľºåħ·
    -0.06
    æ¼Ķç»ĥ
    -0.06
     RFID
    -0.06
    æ¦Ľ
    -0.06
    æ©
    -0.06
     marsh
    -0.06
     forces
    -0.06
    ç¥Ł
    -0.06
    尼奥
    -0.06
    西é£İ
    -0.06
    POSITIVE LOGITS
     Semiconductor
    0.11
    åĻ¨ä»¶
    0.10
     semiconductor
    0.10
     óp
    0.10
     crystal
    0.10
    å®ĿçŁ³
    0.10
     cristal
    0.09
    éĽĨæĪIJçĶµè·¯
    0.09
     Photon
    0.09
    åħīçĶµ
    0.09
    Activations Density 0.066%

    No Known Activations