© 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. 15077
    Prev
    Next
    INDEX
    Explanations

    both or similarly

    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
    laf
    -0.08
    اÙĥ
    -0.07
    inz
    -0.07
    erd
    -0.07
    .googleapis
    -0.07
    ESA
    -0.07
    vement
    -0.07
    asti
    -0.07
    å¼Ł
    -0.07
    ãģ¾ãģĻãģĮ
    -0.07
    POSITIVE LOGITS
     alike
    0.09
    åıĮæĸ¹åľ¨
    0.08
    éĥ½æĺ¯æ¯Ķè¾ĥ
    0.07
     Similarly
    0.07
    bbbb
    0.07
    éĽĻæĸ¹
    0.07
     similarly
    0.07
    ickle
    0.07
     одина
    0.07
    éļıåľ°
    0.07
    Activations Density 0.040%

    No Known Activations