© 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. 27215
    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
    cca
    -0.08
    ewel
    -0.08
     Agung
    -0.08
    utri
    -0.07
    bons
    -0.07
    åħīçģ¯
    -0.07
    embe
    -0.07
    _release
    -0.07
    çĶ¨å¥½
    -0.07
    è¿Ħ
    -0.07
    POSITIVE LOGITS
    rome
    0.07
    ROME
    0.07
    æĭ¬
    0.06
    å°±è¿ij
    0.06
    ĸ
    0.06
    .go
    0.06
    ä¸į移
    0.06
     kick
    0.06
     progression
    0.06
     unr
    0.06
    Activations Density 0.000%

    No Known Activations