© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    chr sequence or number

    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
    ossi
    -0.08
    åªĴ
    -0.07
    å®ŀä¹łæľŁéĹ´
    -0.07
    ipi
    -0.07
    ÑĦиÑĢ
    -0.07
    á»ĩp
    -0.06
    apiro
    -0.06
    ifold
    -0.06
    ires
    -0.06
    å·¥ä½ľæĢģ度
    -0.06
    POSITIVE LOGITS
    çĶŁæł¹
    0.08
    pagesize
    0.07
    reira
    0.07
    ç®ĹäºĨ
    0.07
    udou
    0.07
    Õ¿
    0.07
    robat
    0.07
    ABCDEFGHIJKLMNOP
    0.06
    ixa
    0.06
    dued
    0.06
    Activations Density 0.016%

    No Known Activations