© 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. 41070
    Prev
    Next
    INDEX
    Explanations

    code and academic study references

    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
     Hakim
    -0.09
    ña
    -0.08
    ना
    -0.08
    人æīįç½ij
    -0.08
    adel
    -0.08
    añas
    -0.08
     **.**
    -0.08
    车åıĭ
    -0.08
    å¿«åľ°
    -0.07
    _PP
    -0.07
    POSITIVE LOGITS
    对
    0.09
    身临åħ¶å¢ĥ
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    对æ¯Ķ
    0.07
    çī¹å®ļ
    0.07
    åįĬ
    0.07
    è¾ħåĬ©
    0.07
    ä¸İ
    0.07
    åĬłæĭ¿å¤§çļĦ
    0.07
    对æīĢ
    0.07
    Activations Density 0.001%

    No Known Activations