© 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. 32415
    Prev
    Next
    INDEX
    Explanations

    however, unfortunately, though

    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
    á»ĵi
    -0.08
    æ¶
    -0.07
    åĺĺ
    -0.07
    legen
    -0.07
    мли
    -0.07
    å¾Īåı¯èĥ½æĺ¯
    -0.07
    íħĮê³ł
    -0.07
    ÙħÙĨت
    -0.07
    hell
    -0.07
    REFER
    -0.07
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    è¿ĺå¿ħé¡»
    0.08
    æĢ»æĦŁè§ī
    0.08
    æĪijè¿ĺè¦ģ
    0.07
    è¿ĺæľīä¸ĢçĤ¹
    0.07
    è´¨çĸij
    0.07
    à¹Ģà¸Ĭ
    0.07
    对ä¸Ĭè¿°
    0.07
    è¿ĺéľĢ
    0.07
    è¿ĺåŃĺåľ¨
    0.07
    Activations Density 0.012%

    No Known Activations