© 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. 50036
    Prev
    Next
    INDEX
    Explanations

    FIG

    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
    æīijé¼»
    -0.06
    è¿ħéĢŁåľ°
    -0.06
     âĸ¼
    -0.06
    并æī¿æĭħ
    -0.06
    ä»ĸ们就
    -0.06
    å¯ĤéĿĻ
    -0.06
     sensi
    -0.06
    ãnh
    -0.06
    ä¸ī段
    -0.06
    Utc
    -0.06
    POSITIVE LOGITS
    abet
    0.08
    agers
    0.08
    orable
    0.08
    è¨
    0.08
    asc
    0.07
    广
    0.07
    ÙĦاØŃ
    0.07
    estand
    0.07
    arga
    0.07
    apper
    0.07
    Activations Density 0.005%

    No Known Activations