© 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. 56382
    Prev
    Next
    INDEX
    Explanations

    CG, GC, codon, purine-rich, guanine

    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
    å·®ä¸įå¤ļäºĨ
    -0.06
     operating
    -0.06
    åģļ家åĬ¡
    -0.06
    åĴĮçĶŁæ´»
    -0.06
     Operation
    -0.06
    деÑĤ
    -0.06
    iego
    -0.06
    ÑĪе
    -0.06
    åĬŁçĶ¨
    -0.06
    uli
    -0.06
    POSITIVE LOGITS
    arget
    0.08
    å¤ļè§ģ
    0.08
    -rich
    0.08
    天å®ī
    0.07
    çĶŁçĶŁ
    0.07
    idon
    0.07
    为主çļĦ
    0.07
     عز
    0.07
    ouncill
    0.07
    cluster
    0.07
    Activations Density 0.032%

    No Known Activations