© 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. 14772
    Prev
    Next
    INDEX
    Explanations

    Coupon Code or Gravity and relationship

    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
    ĤŃ
    -0.08
    ten
    -0.08
    odar
    -0.07
    æĭ¨æ¬¾
    -0.07
    ournals
    -0.06
    ijľ
    -0.06
    éĢıæĺİçļĦ
    -0.06
    ÑĥÑģÑĤ
    -0.06
    uff
    -0.06
    åĥıä¸Ģåıª
    -0.06
    POSITIVE LOGITS
    igna
    0.08
    chter
    0.07
    çŁ
    0.07
    ÐĿÐĺЯ
    0.07
    برا
    0.07
     Brun
    0.07
    OptionsMenu
    0.07
     اÙĦأصÙĦ
    0.07
    ancia
    0.07
    _ranges
    0.07
    Activations Density 0.003%

    No Known Activations