© 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. 56840
    Prev
    Next
    INDEX
    Explanations

    here, herein, aqui

    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
    çŁ¥éģĵåIJĹ
    -0.08
    éĢļçŁ¥æĪij
    -0.07
    åijĬè¯īæĪij
    -0.07
    åĨīåĨī
    -0.07
    éĢļçŁ¥æĪij们
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    upun
    -0.07
     meni
    -0.07
    诱
    -0.06
    人è´Ńä¹°
    -0.06
    POSITIVE LOGITS
     here
    0.09
    ç¯ĩå¹ħ
    0.09
     brief
    0.09
     briefly
    0.09
     herein
    0.09
    ç®Ģè¦ģ
    0.09
    æĭĻ
    0.08
    ëĤĺë§Ī
    0.08
    èµĺ
    0.08
     aqui
    0.08
    Activations Density 0.576%

    No Known Activations