© 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. 40649
    Prev
    Next
    INDEX
    Explanations

    risk, access, download, purchases

    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
     tros
    -0.07
    åĦ¿ç§ij
    -0.06
    产ç§ij
    -0.06
    Ïģε
    -0.06
    çļĦ计åĪĴ
    -0.06
    åѤ
    -0.06
    骨èĤī
    -0.06
     trách
    -0.06
     Paste
    -0.06
    å¿ĥè¡Ģ
    -0.06
    POSITIVE LOGITS
    çĶ¨æĪ·åľ¨
    0.11
    à¸Ĥà¸Ńà¸ĩลูà¸ģà¸Ħà¹īา
    0.10
    à¸Ĥà¸Ńà¸ĩà¸ľà¸¹à¹ī
    0.09
    omie
    0.09
    æ¶Īè´¹
    0.09
     isteyen
    0.09
     Bagi
    0.09
    å¸ĪçĶŁ
    0.08
    客æĪ·çļĦéľĢæ±Ĥ
    0.08
    ijker
    0.08
    Activations Density 0.953%

    No Known Activations