© 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. 32601
    Prev
    Next
    INDEX
    Explanations

    Equipment Kits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     (
    -0.06
    ais
    -0.05
    å®ŀä¸ļæľīéĻIJåħ¬åı¸
    -0.05
    INO
    -0.05
    itary
    -0.05
    igas
    -0.05
    åĸ®
    -0.05
     náz
    -0.05
    å¦Ĥæŀľä¸Ģ个
    -0.05
    urement
    -0.05
    POSITIVE LOGITS
    olec
    0.09
    信念
    0.08
    quera
    0.08
    à©į
    0.08
    osten
    0.08
    ssen
    0.08
    oftware
    0.08
    _semaphore
    0.08
    é¦
    0.07
    èĪį
    0.07
    Activations Density 0.022%

    No Known Activations