© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    hash table data structures

    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
    ilot
    -0.08
    ottle
    -0.07
    æ³ķå¾ĭä¿ĿæĬ¤
    -0.07
    ostat
    -0.07
     dim
    -0.06
     royalties
    -0.06
     trace
    -0.06
    schein
    -0.06
    ossa
    -0.06
    Cycle
    -0.06
    POSITIVE LOGITS
     [[]
    0.10
    phu
    0.08
    åħ«åįģ
    0.08
    å±ħæīĢ
    0.08
    ç»ļ
    0.08
    porti
    0.08
    porto
    0.08
    petto
    0.08
    äºĶåįģ
    0.08
    æ°¸å·ŀ
    0.07
    Activations Density 0.005%

    No Known Activations