© 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. 18286
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    جد
    -0.08
    èĻ½çĦ¶çİ°åľ¨
    -0.08
    èĻ½çĦ¶æĪij
    -0.07
    ä½ĨæĦ¿
    -0.07
    å½ĵçĦ¶
    -0.07
     notamment
    -0.07
    座åı³
    -0.07
    ãģ¡ãĤĩãģĨãģ©
    -0.07
    iest
    -0.06
    zcz
    -0.06
    POSITIVE LOGITS
    éĻIJäºİ
    0.09
     loh
    0.08
    rium
    0.08
    äºİæѤ
    0.08
    !',
    0.08
    !]
    0.08
    룬
    0.08
    ä»ħ代表
    0.08
    irim
    0.07
    ante
    0.07
    Activations Density 0.010%

    No Known Activations