© 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. 27006
    Prev
    Next
    INDEX
    Explanations

    custom state .com babies Move view 5 belongs

    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
    aris
    -0.09
    jte
    -0.08
    +xml
    -0.08
    å°ıçļĦæŶåĢĻ
    -0.07
    /qt
    -0.07
    /of
    -0.07
    (ARG
    -0.07
    usc
    -0.07
    ëį©
    -0.07
    _HAVE
    -0.07
    POSITIVE LOGITS
    áĢ®
    0.07
    æĺŁçģ«
    0.06
     explicitly
    0.06
     Explicit
    0.06
     جÙĪ
    0.06
    èĬ±å¼Ģ
    0.06
    бив
    0.06
    _calls
    0.06
    æŀľçĦ¶
    0.06
    explicit
    0.06
    Activations Density 0.001%

    No Known Activations