© 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. 13164
    Prev
    Next
    INDEX
    Explanations

    following metrics

    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
    ril
    -0.09
    _DECL
    -0.08
    é¦Ļå±±
    -0.07
    utsch
    -0.07
    ró
    -0.07
    èµİ
    -0.07
    çıĤ
    -0.07
    anÃŃ
    -0.07
    è´
    -0.07
    裸
    -0.07
    POSITIVE LOGITS
    éŃ
    0.07
     Ra
    0.06
    li
    0.06
    产åĵģçĶŁäº§
    0.06
    anny
    0.06
     pe
    0.06
    ↵↵↵↵↵↵↵↵↵
    0.06
    ëĭ¤ëĬĶ
    0.06
    è§Ħå®ļ
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Activations Density 0.293%

    No Known Activations