© 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. 39056
    Prev
    Next
    INDEX
    Explanations

    adding elements or executing commands

    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
    icone
    -0.07
    ezi
    -0.06
    ezz
    -0.06
    anu
    -0.06
    èī¯å¥½
    -0.06
    atic
    -0.06
    .ini
    -0.06
    dol
    -0.06
    æ±Łå¸Ĥ
    -0.06
    ivo
    -0.06
    POSITIVE LOGITS
    ä»ħæѤ
    0.11
    æĬĬè¿ĻäºĽ
    0.10
    éĢļè¿ĩè¿ĻäºĽ
    0.10
    å°Ĩè¿ĻäºĽ
    0.10
    对ä¸Ĭè¿°
    0.10
    çļĦè¿ĻäºĽ
    0.09
     بÙĩØ°Ùĩ
    0.09
    以ä¸ĬåĨħ容
    0.09
    以ä¸Ĭ
    0.09
    以æѤ
    0.09
    Activations Density 0.151%

    No Known Activations