© 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. 50580
    Prev
    Next
    INDEX
    Explanations

    color and appearance

    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
     struct
    -0.08
    åı¯æ¢¦
    -0.08
    cycles
    -0.08
    ç¦Ħ
    -0.08
    opor
    -0.08
     sprung
    -0.08
     influencing
    -0.07
    å¤ļä¸Ģ份
    -0.07
    森
    -0.07
     ngá»įt
    -0.07
    POSITIVE LOGITS
    ä¸įæĺİæĺ¾
    0.09
    åĽºä½ĵ
    0.08
    evin
    0.08
    å¤ĸè§Ĥ
    0.08
     disappearance
    0.08
    undu
    0.08
    é¢ľèī²
    0.08
    è¿ħéĢŁ
    0.07
    èµıå¿ĥæĤ¦
    0.07
    è¯ķ管
    0.07
    Activations Density 0.023%

    No Known Activations