© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    then / Then; try

    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
    ä¸ĭåIJĮ
    -0.07
    OnError
    -0.06
    once
    -0.06
    icale
    -0.06
    ovid
    -0.06
    è¯Ĩ
    -0.06
    åĽºæľī
    -0.06
    ä½ij
    -0.06
     Grinder
    -0.06
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    POSITIVE LOGITS
    æĽ´éľĢè¦ģ
    0.11
    é¦ĸéĢī
    0.11
    éĢīçĶ¨
    0.11
    éĢĤåIJĪçļĦ
    0.10
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.10
    åIJĪéĢĤçļĦ
    0.10
    éľĢè¦ģçļĦ
    0.09
    éľĢè¦ģ使çĶ¨
    0.09
    éľĢè¦ģä¸Ģ个
    0.09
    æĽ´åºĶ该
    0.09
    Activations Density 0.106%

    No Known Activations