© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37684
    Prev
    Next
    INDEX
    Explanations

    steel, carbon, iron, forged

    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
    Negative Logits
    æģĻ
    -0.08
    èĢ³çĽ®
    -0.07
    ä½ıæĪ·
    -0.07
    ç½Ħ
    -0.07
    çĮľæµĭ
    -0.07
    ç¾²
    -0.07
    éĺ²èĮĥ
    -0.06
    enga
    -0.06
    èĽ¹
    -0.06
    باÙĨ
    -0.06
    POSITIVE LOGITS
     steel
    0.09
    碳
    0.08
    agini
    0.08
    arbon
    0.08
    æĪĸ缺
    0.08
    æĹłç¼ĿéĴ¢ç®¡
    0.08
    æ·¬çģ«
    0.08
    éŁ
    0.07
    éĴ¢
    0.07
     Carbon
    0.07
    Activations Density 0.004%

    No Known Activations