© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16009
    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
    rowse
    -0.07
    ACK
    -0.07
    acks
    -0.06
    oney
    -0.06
    aybe
    -0.06
    obby
    -0.06
    ä»ĸ身ä¸Ĭ
    -0.06
     bro
    -0.06
    aceous
    -0.06
    ack
    -0.06
    POSITIVE LOGITS
    Invoker
    0.07
    roma
    0.07
     Bracket
    0.07
    oter
    0.07
    _MAGIC
    0.07
    æĺ±
    0.07
    rikes
    0.07
    anis
    0.07
    ç¹¼
    0.07
    管çIJĨéĥ¨éŨ
    0.07
    Activations Density 0.000%

    No Known Activations