© 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. 24839
    Prev
    Next
    INDEX
    Explanations

    `+` followed by numbers or Chinese characters

    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
    felder
    -0.07
    stro
    -0.07
    次è¦ģ
    -0.07
    声åĵį
    -0.07
    adian
    -0.07
    åĬłå¿«äºĨ
    -0.07
    åħį
    -0.07
    á»ĭn
    -0.07
    sgi
    -0.07
    ivia
    -0.07
    POSITIVE LOGITS
    nul
    0.08
    éľĸ
    0.07
    puter
    0.07
    åı¯è§Ĩ
    0.07
    åŃ¦ä¹łæķĻèĤ²
    0.07
    gene
    0.06
    ä»Ĭ天å°ıç¼ĸå°±
    0.06
    åįļ客
    0.06
    .Override
    0.06
    çĭĤ
    0.06
    Activations Density 0.001%

    No Known Activations