© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26174
    Prev
    Next
    INDEX
    Explanations

    speed over a hill

    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
    缴ãģĹ
    -0.07
    shal
    -0.07
    æĹłç©·çļĦ
    -0.07
     potency
    -0.07
    åľ£è´¤
    -0.07
    åı°åĮº
    -0.07
    å°ıåŃIJ
    -0.07
    纵横
    -0.07
    ä¸įæĪIJ
    -0.07
    setWidth
    -0.07
    POSITIVE LOGITS
     momentarily
    0.08
     downward
    0.08
     upward
    0.08
    ç£
    0.07
    çĤ¹æѤ
    0.07
    åŃĺåľ¨æĦŁ
    0.07
    æѤæŶ
    0.07
    iceps
    0.07
    æī¿åıĹçļĦ
    0.07
     susp
    0.07
    Activations Density 0.005%

    No Known Activations