© 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. 27656
    Prev
    Next
    INDEX
    Explanations

    relations, -fold, derivative, parity

    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
     trans
    -0.06
     mas
    -0.06
     vis
    -0.06
    éĩijé¾Ļ
    -0.06
    amid
    -0.06
    äºĮèĢħ
    -0.05
     ver
    -0.05
     dat
    -0.05
    .link
    -0.05
    åħį
    -0.05
    POSITIVE LOGITS
    åľ¨ä¸Ĭè¿°
    0.10
    örd
    0.09
    对ä¸Ĭè¿°
    0.09
    æĬķèµĦ管çIJĨæľīéĻIJåħ¬åı¸
    0.08
    nard
    0.08
     Pej
    0.08
    nesia
    0.08
    infeld
    0.08
    annotate
    0.08
    inä
    0.07
    Activations Density 0.023%

    No Known Activations