© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    steroids and cyclic compounds

    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
    uha
    -0.08
    imately
    -0.08
    群ä¼ĹåĬŀå®ŀäºĭ
    -0.07
    itim
    -0.07
    åıį
    -0.07
    çļĦæĥħ绪
    -0.07
    ÙĪÙĨÙĬا
    -0.07
    稣
    -0.07
    zza
    -0.07
    æ¯Ĵ
    -0.07
    POSITIVE LOGITS
    wad
    0.07
    诺è¨Ģ
    0.07
    lop
    0.06
    åħ¶åIJį
    0.06
    pper
    0.06
    adak
    0.06
    å°±å®ĮæĪIJäºĨ
    0.06
    adro
    0.06
    åĽ½éŨ
    0.06
    ÑĪке
    0.06
    Activations Density 1.115%

    No Known Activations