© 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. 40112
    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
    åĽ½å®Ŀ
    -0.08
    almaz
    -0.07
    ¬ģ
    -0.07
    åħ´
    -0.07
    .fm
    -0.07
    jú
    -0.07
    pees
    -0.07
     inseg
    -0.07
     вол
    -0.06
     munic
    -0.06
    POSITIVE LOGITS
    å°±è¿ij
    0.07
     europ
    0.07
    ÅĽni
    0.07
    ression
    0.06
    å°ıéĻ¢
    0.06
    PLUGIN
    0.06
    ãģĵãĤĵãģ«
    0.06
    aptive
    0.06
    .har
    0.06
    .eu
    0.06
    Activations Density 0.000%

    No Known Activations