© 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. 23979
    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
    æŃ£åIJij
    -0.07
    unaan
    -0.07
     forwards
    -0.07
    cy
    -0.07
     boule
    -0.07
    oter
    -0.06
    ty
    -0.06
    ny
    -0.06
    üssel
    -0.06
    èĩªçĦ¶
    -0.06
    POSITIVE LOGITS
    ä¹ı
    0.08
    ummer
    0.08
    latin
    0.08
    æīĺ管
    0.07
    lua
    0.07
    obre
    0.07
     götür
    0.07
    å³Ń
    0.07
    utdown
    0.07
    ÑĥÑĢÑģ
    0.07
    Activations Density 0.000%

    No Known Activations