© 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. 17009
    Prev
    Next
    INDEX
    Explanations

    age ranges or specific numbers

    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
    åİĨåİĨ
    -0.08
    ãģĹãģĭ
    -0.07
    ieden
    -0.07
    åıĪåĥı
    -0.07
    zel
    -0.07
    ä¸ĭä¸ĢåĪ»
    -0.07
    ä¸īæĸ¹éĿ¢
    -0.07
     Britt
    -0.07
    çĦ¶å¤§
    -0.07
    éĤ£ä¸¤ä¸ª
    -0.07
    POSITIVE LOGITS
    idium
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    endam
    0.07
    Requested
    0.07
    essor
    0.07
    OutOfRange
    0.07
    سع
    0.06
    ensem
    0.06
    éłĵæĻĤ
    0.06
    çļĦåħ·ä½ĵæĥħåĨµ
    0.06
    Activations Density 0.033%

    No Known Activations