© 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. 62627
    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
    ิà¸Ķ
    -0.07
    forg
    -0.07
     somehow
    -0.07
    รว
    -0.07
    _GLOBAL
    -0.07
    èįIJ
    -0.07
    èįĨ
    -0.07
    REP
    -0.07
    顶
    -0.06
    åĩłåĪĨ
    -0.06
    POSITIVE LOGITS
    اÙĨÙĩ
    0.08
    enheim
    0.07
    estens
    0.07
     baseline
    0.06
    ä¿¡è¾¾
    0.06
    -contrib
    0.06
    Ñģпа
    0.06
    estet
    0.06
     sobrev
    0.06
    ansk
    0.06
    Activations Density 0.000%

    No Known Activations