© 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. 15282
    Prev
    Next
    INDEX
    Explanations

    simply trying to utilize

    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
     deput
    -0.08
    ixe
    -0.07
    ardin
    -0.06
    å°ıé¾Ļ
    -0.06
    ADI
    -0.06
    æ¶ī
    -0.06
    yt
    -0.06
    ekl
    -0.06
    atal
    -0.06
    lian
    -0.06
    POSITIVE LOGITS
    æīĢæĢĿ
    0.08
    Simply
    0.08
    æ¯Ľ
    0.08
     Simply
    0.08
     simply
    0.08
    ä»ħä»ħæĺ¯
    0.07
    åħį费注åĨĮ
    0.07
    éĢļ天
    0.07
    ondo
    0.07
    å¾Īç®Ģåįķ
    0.07
    Activations Density 0.102%

    No Known Activations