© 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. 61460
    Prev
    Next
    INDEX
    Explanations

    ManhattanConnectionRouter

    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
    oku
    -0.07
    andı
    -0.07
    èµ
    -0.06
    继ç»Ńéĺħ读
    -0.06
    anom
    -0.06
    Thor
    -0.06
     supposed
    -0.06
     Directory
    -0.06
    ux
    -0.06
    éķĩéĿĻ
    -0.06
    POSITIVE LOGITS
    ä½įæķ°
    0.07
    amkan
    0.07
    аве
    0.07
    JO
    0.07
    akis
    0.07
    æī°
    0.07
    wege
    0.07
    jt
    0.07
    -hooks
    0.07
    rez
    0.07
    Activations Density 0.177%

    No Known Activations