© 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. 2778
    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
    edException
    -0.09
    ness
    -0.09
    常人
    -0.09
    igs
    -0.09
    人以ä¸ĭ
    -0.08
    çĿĢä¸Ģ
    -0.08
    åıĬ管çIJĨ
    -0.08
    	TokenName
    -0.08
    lessly
    -0.08
    çĿĢ头
    -0.08
    POSITIVE LOGITS
    tte
    0.07
    ues
    0.06
    ature
    0.06
    etje
    0.06
    Ñİ
    0.06
     about
    0.06
    ìį¨
    0.06
     nature
    0.06
    -like
    0.06
    ummer
    0.06
    Activations Density 0.000%

    No Known Activations