© 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. 50041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ulte
    -0.07
     Bauch
    -0.07
    iba
    -0.06
    Insets
    -0.06
    çŀ³
    -0.06
     inters
    -0.06
    heber
    -0.06
    ä¸į使çĶ¨
    -0.06
    åħļé£İ
    -0.06
    átk
    -0.06
    POSITIVE LOGITS
     dividend
    0.07
    åĩĨå¤ĩ好çļĦ
    0.07
    å°ıçļĦæŶåĢĻ
    0.07
    omo
    0.07
    esi
    0.07
    éļ±ç§ģæ¬Ĭ
    0.07
    amo
    0.07
     mentally
    0.07
    fahrten
    0.07
    FromArray
    0.07
    Activations Density 0.000%

    No Known Activations