© 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. 20638
    Prev
    Next
    INDEX
    Explanations

    first/second/primary/common/new

    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
     in
    -0.06
    ats
    -0.06
    iras
    -0.06
    for
    -0.05
    full
    -0.05
    r
    -0.05
    cell
    -0.05
    éĤ£æĺ¯
    -0.05
    éĤ£çĤ¹
    -0.05
    efe
    -0.05
    POSITIVE LOGITS
    ฯ
    0.11
    家ä¼Ļ
    0.09
    å®ŀæĻ¯åĽ¾
    0.08
    IVED
    0.08
    quinho
    0.08
    åħļå·¥å§Ķ
    0.08
    æŃ£å¤Ħäºİ
    0.08
    ULATOR
    0.07
    è§ī
    0.07
    úl
    0.07
    Activations Density 0.043%

    No Known Activations