© 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. 22902
    Prev
    Next
    INDEX
    Explanations

    legal/official document elements

    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
    饶
    -0.07
    egn
    -0.07
    zó
    -0.07
    _pb
    -0.06
    ya
    -0.06
    ä¸įå¤ļ说
    -0.06
    æµ®
    -0.06
     maest
    -0.06
    设计åħ¬åı¸
    -0.06
    imetr
    -0.06
    POSITIVE LOGITS
    çľ·
    0.08
    lach
    0.08
    oran
    0.08
    ãĥ¯ãĤ¯ãĥģãĥ³
    0.07
    ì°©
    0.07
    Unnamed
    0.07
    bacher
    0.07
    é´
    0.07
    ÙĨÙģ
    0.07
    ovel
    0.07
    Activations Density 0.026%

    No Known Activations