© 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. 26320
    Prev
    Next
    INDEX
    Explanations

    correctness of dialog or versions

    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
    åĢ¤
    -0.08
     Bakal
    -0.08
    éĺĪåĢ¼
    -0.07
     adaptive
    -0.07
    çĥ¤æ¼Ĩ
    -0.07
    åĢ¼æĺ¯
    -0.07
    acce
    -0.07
    celli
    -0.07
    rix
    -0.07
     Adaptive
    -0.07
    POSITIVE LOGITS
    æĭĨåĪĨ
    0.08
    uenta
    0.08
    iom
    0.08
    æĸ¹ç¨ĭå¼ı
    0.08
    ç®ĢåĮĸ
    0.08
    èįī稿
    0.08
     rearr
    0.08
    è§ĦèĮĥçļĦ
    0.07
     net
    0.07
    å®Įæķ´çļĦ
    0.07
    Activations Density 0.002%

    No Known Activations