© 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. 33084
    Prev
    Next
    INDEX
    Explanations

    gear-equipped, high hardness, top molds

    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
    åİŁæľīçļĦ
    -0.07
    çļĦ缮çļĦæĺ¯
    -0.07
    çļĦæľīåħ³
    -0.07
    åİŁæľī
    -0.07
     [#
    -0.07
    fram
    -0.07
     #:
    -0.07
    ád
    -0.07
    çļĦè¿ĺæĺ¯
    -0.07
    clid
    -0.07
    POSITIVE LOGITS
    çļĦæĸ°åŀĭ
    0.09
    åľ¨åĨħçļĦ
    0.08
    好å¤ĦçļĦ
    0.08
    çļĦå°ıåŀĭ
    0.08
     olev
    0.08
    ç¥ī
    0.08
     वालà¥ĩ
    0.08
     वाल
    0.08
    äºİä¸Ģä½ĵçļĦ
    0.08
    为主çļĦ
    0.08
    Activations Density 0.430%

    No Known Activations