© 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. 9949
    Prev
    Next
    INDEX
    Explanations

    molecular weight and polymer chains

    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
     lou
    -0.08
    alc
    -0.07
    insen
    -0.07
    缴å°Ħ
    -0.06
    è¹²
    -0.06
    è§ĴçļĦ
    -0.06
    è´Łåİĭ
    -0.06
    باÙĨ
    -0.06
    å¹³çļĦ
    -0.06
    çŁ³éŨ
    -0.06
    POSITIVE LOGITS
    åĪĨåŃIJéĩı
    0.10
     backbone
    0.10
    åĪĨåŃIJ
    0.10
     polymer
    0.10
    ç¼Ģ
    0.09
    段
    0.09
    chains
    0.09
    å¾Īéķ¿
    0.09
     chains
    0.09
     length
    0.09
    Activations Density 0.110%

    No Known Activations