© 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. 56566
    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
     really
    -0.07
    ton
    -0.07
    åħĭåħ°
    -0.06
    ä¿¡
    -0.06
    entin
    -0.06
    å§ĭ
    -0.06
    idth
    -0.06
     Karr
    -0.06
    å£ķ
    -0.06
    anged
    -0.06
    POSITIVE LOGITS
    anak
    0.09
    stw
    0.08
    intr
    0.08
    à¹Ģส
    0.08
    unlock
    0.07
    æĸ¹æ¡Ī设计
    0.07
    .imag
    0.07
    unjung
    0.07
    ecast
    0.07
     tales
    0.07
    Activations Density 0.000%

    No Known Activations