© 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. 28549
    Prev
    Next
    INDEX
    Explanations

    percentage or times increases

    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
    产
    -0.07
    ä¸ĭå±Ĥ
    -0.07
    ä¸ĭ
    -0.07
    _TXT
    -0.07
    åľ¨ä¸ĭ
    -0.07
    haut
    -0.07
    ulier
    -0.07
     оÑģÑĤ
    -0.07
     Äįin
    -0.07
     azon
    -0.07
    POSITIVE LOGITS
    â
    0.07
    FN
    0.07
    磶
    0.07
    _fds
    0.07
    åĨ°å±±
    0.07
    æ±Łæµ·
    0.06
    ndata
    0.06
    ¤íĶ
    0.06
    å¢ĥå¤ĸè¾ĵåħ¥
    0.06
    aad
    0.06
    Activations Density 0.076%

    No Known Activations