© 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. 22778
    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    plib
    -0.06
    没说
    -0.06
     encom
    -0.06
    alamat
    -0.06
    ebol
    -0.06
    _PIX
    -0.06
    OutOf
    -0.06
    ä½ĵç³»
    -0.06
    .requestFocus
    -0.06
    POSITIVE LOGITS
     ngh
    0.08
    utherford
    0.07
    .fun
    0.07
     funk
    0.07
    retty
    0.07
    ÙħاÙħ
    0.07
    çľĭåĪ°è¿ĻéĩĮ
    0.07
    typing
    0.07
    ìĤ´
    0.07
    odu
    0.07
    Activations Density 0.000%

    No Known Activations