© 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. 43947
    Prev
    Next
    INDEX
    Explanations

    code directives and comments

    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
    好åĥıæĺ¯
    -0.07
    chn
    -0.07
    erot
    -0.07
     seem
    -0.07
    ä¼¼ä¹İæĺ¯
    -0.07
    ç¿Ķ
    -0.07
    odob
    -0.07
    å©·
    -0.07
    èħ¾
    -0.07
    好åĥıåľ¨
    -0.07
    POSITIVE LOGITS
    untas
    0.07
     λοι
    0.07
    éĨ
    0.07
    Buzz
    0.07
    nado
    0.07
    boxed
    0.06
     vollkommen
    0.06
     Ñģмело
    0.06
    buzz
    0.06
    ercul
    0.06
    Activations Density 0.005%

    No Known Activations