© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15837
    Prev
    Next
    INDEX
    Explanations

    modify it

    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
    å¤§ä½ľæĪĺ
    -0.09
    ÑĻÑĥ
    -0.09
    меÑĢÑĭ
    -0.09
    arest
    -0.08
    ¶ļ
    -0.08
    åįĹåĽ½
    -0.08
    éĺħè¯»æľ¬æĸĩ
    -0.08
     lévÅij
    -0.08
    leiding
    -0.08
    ми
    -0.08
    POSITIVE LOGITS
    0.07
    å¾Ĺèµ·
    0.06
    0.06
    0.06
    ãĢĢ
    0.06
    并å®ĮæĪIJ
    0.06
    å¾Ĺä¸Ĭ
    0.06
    çĶŁåľ¨
    0.05
    “
    0.05
    obia
    0.05
    Activations Density 0.008%

    No Known Activations