© 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. 27178
    Prev
    Next
    INDEX
    Explanations

    innovations, ruling, case, compression, feelings

    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
    .glob
    -0.08
    rets
    -0.08
     therefore
    -0.07
     поÑįÑĤомÑĥ
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
    ä½ľåĪĻ
    -0.07
     dunque
    -0.07
     donc
    -0.07
    åĽłæѤ
    -0.07
     Therefore
    -0.06
    POSITIVE LOGITS
    并ä¸į代表
    0.09
    并ä¸įæĦıåij³çĿĢ
    0.09
    ä¹Łåıªæĺ¯
    0.09
    åıªæĺ¯
    0.09
    åıªæĺ¯ä¸Ģ个
    0.09
     alone
    0.08
    ä»ħæıIJä¾Ľ
    0.08
    ä»ħ代表
    0.08
    åıªæĺ¯ä¸Ģ
    0.08
    并ä¸įæĺ¯
    0.08
    Activations Density 0.124%

    No Known Activations