© 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. 23366
    Prev
    Next
    INDEX
    Explanations

    ion movement and exchange

    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¤Ħéķ¿
    -0.08
    å¤Ħ
    -0.07
    æµ·éģĵ
    -0.07
    çĦ¶åIJİçĶ¨
    -0.07
    lain
    -0.07
    Bins
    -0.07
    dze
    -0.06
     sostenibilitÃł
    -0.06
    æĬ¬é«ĺ
    -0.06
    ä¸ŃçĶŁ
    -0.06
    POSITIVE LOGITS
    çļĦ移åĬ¨
    0.08
     incoming
    0.08
     movement
    0.08
     exchange
    0.08
    移åĬ¨
    0.08
    个头
    0.08
    apati
    0.08
    åıĤä¸İ
    0.08
    移åĬ¨åĪ°
    0.08
    exchange
    0.07
    Activations Density 0.018%

    No Known Activations