© 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. 16986
    Prev
    Next
    INDEX
    Explanations

    specimens convicting Franks heavy duty

    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
    HR
    -0.07
    ich
    -0.06
     HR
    -0.06
    ä¿Ŀéļľ
    -0.06
    èĩ³å°ijåľ¨
    -0.06
    æīĢæľīçļĦ
    -0.06
    —
    -0.06
    ito
    -0.06
    æĶ¾æ°´
    -0.05
    åĢĻ
    -0.05
    POSITIVE LOGITS
    Ãłi
    0.10
    ognito
    0.09
    ehold
    0.08
    éŁ³ä¹IJåѦéĻ¢
    0.08
    çļĭ
    0.08
    esas
    0.08
    edan
    0.08
     ImVec
    0.08
    enburg
    0.08
    CHIP
    0.08
    Activations Density 0.002%

    No Known Activations