© 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. 61421
    Prev
    Next
    INDEX
    Explanations

    variable or mathematical expressions with `v`

    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
    对客æĪ·
    -0.07
    ׾ק
    -0.07
    èĤĦ
    -0.07
    iton
    -0.07
    indr
    -0.07
    itag
    -0.07
    æĺĵçĪĨ
    -0.07
     Mosk
    -0.07
    çľĭäºĨä¸Ģä¸ĭ
    -0.07
    å¿ĺè®°äºĨ
    -0.07
    POSITIVE LOGITS
    éĩįéĩį
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    å¾·æĸ¯
    0.06
    çIJĨ
    0.06
    æĶ¯åħ¬åı¸
    0.06
    armo
    0.06
    akkan
    0.06
    ymm
    0.06
     rest
    0.06
    æľĢåĪĿ
    0.06
    Activations Density 0.004%

    No Known Activations