© 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. 59017
    Prev
    Next
    INDEX
    Explanations

    No, When, Initially, Contact

    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
    ess
    -0.08
    edo
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    å¼Ģåı£è¯´éģĵ
    -0.07
    atge
    -0.06
    ella
    -0.06
    ingin
    -0.06
    çĸ®
    -0.06
    ì¦Į
    -0.06
    çĹ´
    -0.06
    POSITIVE LOGITS
    irsch
    0.08
    ook
    0.07
    ä¾ĥ
    0.07
    åĽłä¸ºæĺ¯
    0.07
    Utf
    0.07
    hots
    0.07
    Laughs
    0.07
    czo
    0.07
    è¤ĩ
    0.07
    qiq
    0.07
    Activations Density 0.136%

    No Known Activations