© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    global, generally

    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
     Ter
    -0.08
    agod
    -0.07
    æ§IJ
    -0.07
    çIJĨæĥ³
    -0.07
     MD
    -0.07
    ä¸įåĪĨ
    -0.07
    è¿ĻäºĽåĽłç´ł
    -0.07
    å³
    -0.07
    å°ıæľī
    -0.06
    æĪij常常
    -0.06
    POSITIVE LOGITS
    並ãģ³
    0.08
    igt
    0.08
     menet
    0.08
    INN
    0.07
    åħ¶å®ĥçļĦ
    0.07
    éĽ¯
    0.07
    zin
    0.07
    acco
    0.07
    lem
    0.07
    åħ¶å®ĥ
    0.07
    Activations Density 0.375%

    No Known Activations