© 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. 59069
    Prev
    Next
    INDEX
    Explanations

    code block delimiter

    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
     Heard
    -0.07
    ouch
    -0.07
    asen
    -0.06
    åijµåijµ
    -0.06
    æ¶Ľ
    -0.06
    éĵ®
    -0.06
    atica
    -0.06
     commonplace
    -0.06
    åı¯è§ģ
    -0.06
    寿
    -0.06
    POSITIVE LOGITS
    以ä¸ĭ为
    0.09
    代çłģå¦Ĥä¸ĭ
    0.08
    ä¸ĭ表
    0.07
    aco
    0.07
    è¿Ļ个æĸ¹æ³ķ
    0.07
    ä»ĺ诸
    0.07
    unde
    0.07
    burgh
    0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.07
    performance
    0.07
    Activations Density 0.036%

    No Known Activations