© 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. 34001
    Prev
    Next
    INDEX
    Explanations

    rel or Rev

    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
    ding
    -0.07
    åĪ«èĩ´
    -0.07
    éĶ¦æ±Ł
    -0.07
    To
    -0.06
    ism
    -0.06
    åĪ«è¯´
    -0.06
    òng
    -0.06
     Basta
    -0.06
    burg
    -0.06
    éĵ¶å±ij
    -0.06
    POSITIVE LOGITS
    arena
    0.08
    arend
    0.08
    utherford
    0.08
    ystore
    0.08
    赫
    0.08
    åħ°è¾¾
    0.07
    ç¦ı
    0.07
    elis
    0.07
    arde
    0.07
    سÙĪب
    0.07
    Activations Density 0.086%

    No Known Activations