© 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. 57134
    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
    acquis
    -0.07
     acquis
    -0.07
     Rosenstein
    -0.06
    .removeEventListener
    -0.06
    orian
    -0.06
    åIJ¹åĵį
    -0.06
     Ah
    -0.06
    aisia
    -0.06
    еÑĢна
    -0.06
    彬彬
    -0.06
    POSITIVE LOGITS
    ipt
    0.07
    å½°
    0.07
    ç½ijåıĭè¯Ħ论
    0.07
    ouz
    0.07
     desemp
    0.07
    cke
    0.07
    御
    0.07
    oo
    0.07
    æµĭæݧ
    0.07
    inet
    0.07
    Activations Density 0.000%

    No Known Activations