© 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. 42987
    Prev
    Next
    INDEX
    Explanations

    sides and connecting walls

    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
     Centrale
    -0.07
    åī¥ç¦»
    -0.07
    ä¸ĢåĽ¢
    -0.07
    orough
    -0.06
    ศูà¸Ļยà¹Įà¸ģลาà¸ĩ
    -0.06
    ston
    -0.06
    æµ®
    -0.06
    两级
    -0.06
    rana
    -0.06
    stein
    -0.06
    POSITIVE LOGITS
    ngth
    0.09
    Ùĩار
    0.08
     lengths
    0.08
     connecting
    0.08
    ugi
    0.08
    è¾ĥçŁŃ
    0.07
    Powered
    0.07
    verbind
    0.07
    connecting
    0.07
    -length
    0.07
    Activations Density 0.010%

    No Known Activations