© 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. 24757
    Prev
    Next
    INDEX
    Explanations

    reduction of resistance

    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
    צר
    -0.07
    俨
    -0.07
    Bre
    -0.06
    æłij人
    -0.06
    ä¼ģä¸ļæ³ķ人
    -0.06
    çĴĢ
    -0.06
    å±±åı£
    -0.06
    å®°
    -0.06
    ç»´åħĭ
    -0.06
    agai
    -0.06
    POSITIVE LOGITS
    ä¸į容æĺĵ
    0.09
    æĽ´åĬłçļĦ
    0.09
    ä¸įæĺĵ
    0.08
    éģ¿åħįäºĨ
    0.08
    ä¸įä½Ĩ
    0.07
     furthermore
    0.07
    åĩıå°ij对
    0.07
    éĢļè¿ĩ使çĶ¨
    0.07
    æŀģ大çļĦ
    0.07
    tober
    0.07
    Activations Density 0.866%

    No Known Activations