© 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. 27736
    Prev
    Next
    INDEX
    Explanations

    creams or money

    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
    itched
    -0.08
    æĹłéľĢ
    -0.08
    æīįæľīäºĨ
    -0.07
    chetta
    -0.07
    ä¸įéľĢ
    -0.07
    æ²³æ±ł
    -0.07
    .Unmarshal
    -0.07
    inheit
    -0.07
    äºĮè¯Ŀ
    -0.07
    .Optional
    -0.07
    POSITIVE LOGITS
    ä¹ŁæĹłæ³ķ
    0.12
    åıªèĥ½
    0.12
    并ä¸įèĥ½
    0.11
    ä¹Łåıªèĥ½
    0.11
     alone
    0.11
    ä¸įèĥ½å®Įåħ¨
    0.11
    æīĢèĥ½
    0.10
    è¯ķåĽ¾
    0.10
    ãģłãģijãģ§ãģ¯
    0.10
    ä¹Łéļ¾ä»¥
    0.10
    Activations Density 0.242%

    No Known Activations