© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    percentages and results

    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
    çģµå±±
    -0.08
    åĸľéĹ»
    -0.08
    ssia
    -0.08
    .isFile
    -0.07
    翻天
    -0.07
    çļĦ代çłģ
    -0.07
    çļĦæĢĿç»´
    -0.07
    Recognition
    -0.07
    å¿ĥæĢĿ
    -0.07
    æĺ¯å¥½
    -0.07
    POSITIVE LOGITS
    è¿Ļæĺ¯åĽłä¸º
    0.12
    åı¯èĥ½æĺ¯åĽłä¸º
    0.12
     due
    0.12
    æĺ¯åĽłä¸º
    0.11
    éĤ£æĺ¯åĽłä¸º
    0.11
    due
    0.10
    è¿Ļæĺ¯çĶ±äºİ
    0.10
    æĢİä¹ĪåĽŀäºĭ
    0.10
     apparently
    0.09
    æĺ¯çĶ±äºİ
    0.09
    Activations Density 0.116%

    No Known Activations