© 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. 30525
    Prev
    Next
    INDEX
    Explanations

    mechanism

    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
    åħį
    -0.08
    åħ¶èĩªçĦ¶
    -0.08
    é£ŁãģĦ
    -0.07
    æĤ£äºĨ
    -0.07
    åģļäºĽ
    -0.07
    éĺij
    -0.07
    iec
    -0.07
    æµĭè¯ķç»ĵæŀľ
    -0.07
    ecer
    -0.06
     geograf
    -0.06
    POSITIVE LOGITS
     Wohl
    0.09
     étapes
    0.09
    æŃ¥éª¤
    0.09
     stages
    0.09
    à¸Ĥัà¹īà¸Ļà¸ķà¸Ńà¸Ļ
    0.08
     intermedi
    0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.08
    è¿ĩç¨ĭçļĦ
    0.08
    çļĦåħ¨è¿ĩç¨ĭ
    0.08
    第ä¸ĢæŃ¥
    0.08
    Activations Density 0.005%

    No Known Activations