© 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. 24657
    Prev
    Next
    INDEX
    Explanations

    http, sed, SET

    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
    åĬłæĭ¿å¤§
    -0.08
     (
    -0.08
    æĸ°åĬłåĿ¡
    -0.07
    ,
    -0.06
    å®ĥæīĢ
    -0.06
    åħ¶
    -0.06
    æĢ§ä»¥åıĬ
    -0.06
    对å®ĥ
    -0.06
    —that
    -0.06
    åħ¶çľŁå®ŀæĢ§
    -0.06
    POSITIVE LOGITS
    ãģŁãĤī
    0.09
    inerary
    0.08
    ãģ¿ãģ®
    0.08
    è¿ĶåĽŀ顶éĥ¨
    0.08
    ehan
    0.08
     halinde
    0.08
     Kirim
    0.08
    νοÏį
    0.08
     steig
    0.08
    TypeDef
    0.08
    Activations Density 0.083%

    No Known Activations