© 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. 57058
    Prev
    Next
    INDEX
    Explanations

    vehicle components, aircraft parts

    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
    å°ī
    -0.07
    婧
    -0.07
    主人ç¿ģ
    -0.07
     zdro
    -0.07
    Username
    -0.07
    reate
    -0.07
    MainThread
    -0.07
    èĩªå·±
    -0.07
    oulos
    -0.07
    ael
    -0.07
    POSITIVE LOGITS
    è¥Ł
    0.08
     вÑĭдви
    0.08
     retract
    0.08
     emergency
    0.08
    ç´§æĢ¥
    0.07
    ogu
    0.07
    (levels
    0.07
    ÑĢек
    0.07
    shal
    0.07
    é¾Ļåĩ¤
    0.07
    Activations Density 0.023%

    No Known Activations