© 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. 50609
    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
     matters
    -0.07
    adam
    -0.07
    amas
    -0.06
     Matters
    -0.06
     matter
    -0.06
     foll
    -0.06
    æѤå¤Ħ
    -0.06
     Leid
    -0.06
    .Parser
    -0.06
    å¾Ĺåĩºç»ĵ论
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.10
    åĬłæĭ¿å¤§
    0.09
    forsch
    0.08
    æĿijæĿij
    0.07
    ruk
    0.07
    éĽĨåħ¨
    0.07
     traumatis
    0.07
    jep
    0.07
    aar
    0.07
    å¼łå»º
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.