© 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. 31735
    Prev
    Next
    INDEX
    Explanations

    I need to write

    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
    oj
    -0.07
    راÙĩ
    -0.07
    èĥĮåIJİçļĦ
    -0.07
    票æķ°
    -0.06
    æ¦Ĥæĭ¬
    -0.06
    åįĹåĽ½
    -0.06
     underlying
    -0.06
    èģĶ社
    -0.06
    å¿«çľĭ
    -0.06
    æ
    -0.06
    POSITIVE LOGITS
    åĽ
    0.08
    æĥ³æī¾
    0.08
    æī¾åĩº
    0.07
    arin
    0.07
    ãģªãģ®ãģ§ãģĹãĤĩãģĨ
    0.07
    å½ĵåħ¶
    0.07
    åľ¨è¿Ļæł·çļĦ
    0.07
    åıĸåħ¶
    0.07
    å¨ģ
    0.07
    çĶ±åħ¶
    0.07
    Activations Density 0.254%

    No Known Activations