© 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. 42447
    Prev
    Next
    INDEX
    Explanations

    transportation or communication mode

    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
    ianne
    -0.08
    ä»Ķ
    -0.08
    вига
    -0.08
    åĨįéĢł
    -0.08
    çݩ家å°Ĩ
    -0.07
     vergle
    -0.07
    åIJİèĢħ
    -0.07
    ater
    -0.07
    chnet
    -0.07
    áĥIJáĥķ
    -0.07
    POSITIVE LOGITS
    æŃ¤æ¥¼
    0.07
    åľ¨æŁIJ
    0.07
    Roy
    0.07
    æľīä¸ĭåĪĹ
    0.07
    婺
    0.06
    epak
    0.06
    âĪ
    0.06
     Mathematic
    0.06
    çĪ±æĬ¤
    0.06
    elok
    0.06
    Activations Density 0.010%

    No Known Activations