© 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. 62858
    Prev
    Next
    INDEX
    Explanations

    electron transfer or flow

    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
    bedingt
    -0.06
    gel
    -0.06
    èĩªè´¹
    -0.06
    åīĸ
    -0.06
    éŃ
    -0.06
    é«ĺç²¾
    -0.06
    æ²¹çĽIJ
    -0.06
     breath
    -0.06
    æıĴ
    -0.06
    Ñģок
    -0.06
    POSITIVE LOGITS
    crement
    0.08
    ources
    0.08
    çīĩçīĩ
    0.07
    /thumb
    0.07
    imbus
    0.07
    ë¹Į
    0.07
    è³
    0.07
    ToObject
    0.07
     поко
    0.07
    ãģ£ãģ±
    0.07
    Activations Density 0.004%

    No Known Activations