© 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. 3489
    Prev
    Next
    INDEX
    Explanations

    same or matched groups

    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
     Tent
    -0.07
    lobals
    -0.07
    æĹłæŃ¢å¢ĥ
    -0.06
    åĪ©
    -0.06
    æģĭ
    -0.06
    ité
    -0.06
    åijĪ
    -0.06
    obi
    -0.06
    nar
    -0.06
    oyal
    -0.06
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.15
    缸åIJĮçļĦ
    0.14
    缸åIJĮ
    0.13
    åIJĦèĩª
    0.13
     одина
    0.12
     åIJĮãģĺ
    0.11
    è¿Ľè¡Įæ¯Ķè¾ĥ
    0.11
     identical
    0.10
    åIJĮçŃī
    0.10
    å®ĥ们çļĦ
    0.10
    Activations Density 0.008%

    No Known Activations