© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20390
    Prev
    Next
    INDEX
    Explanations

    order, then remaining

    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
    ä»Ĺ
    -0.08
    ضا
    -0.08
    å¾ĭ
    -0.07
    xn
    -0.07
    yum
    -0.07
    å¤ļå¤Ħ
    -0.07
    ä¹Łåı¯çĽ´æİ¥
    -0.07
    acan
    -0.07
    è¾Ĺ转
    -0.06
     ÐĸÑĥ
    -0.06
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.08
    _Instance
    0.08
    çĦ¶åIJİæĺ¯
    0.08
    ezas
    0.08
    è¦ģçľĭ
    0.08
     fer
    0.07
    ely
    0.07
    å±ħåīį
    0.07
     slightly
    0.07
    _published
    0.07
    Activations Density 0.022%

    No Known Activations