© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20400
    Prev
    Next
    INDEX
    Explanations

    person impersonating

    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
     Anc
    -0.07
    Adj
    -0.07
    éĻį
    -0.07
    çľ¼
    -0.07
    çİ°ä»·
    -0.07
    Anc
    -0.07
     Adj
    -0.07
    /english
    -0.07
    çĪ±å°Ķ
    -0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.07
    POSITIVE LOGITS
    æľªç»ıæİĪæĿĥ
    0.09
     delegation
    0.09
    _bind
    0.09
    æİĪæĿĥå§Ķæīĺ书
    0.08
    bind
    0.08
    æ¬łç¼º
    0.08
    书éĿ¢æİĪæĿĥ
    0.08
    åĹ£
    0.07
     proxies
    0.07
    å§Ķæīĺ书
    0.07
    Activations Density 0.010%

    No Known Activations