© 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. 34183
    Prev
    Next
    INDEX
    Explanations

    quantity of substance

    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¸Ģ个
    -0.07
    éģ½
    -0.07
    LTR
    -0.07
    ä¸Ģéĥİ
    -0.07
    baugh
    -0.07
    åı°åķĨ
    -0.06
    ISC
    -0.06
    anÃŃ
    -0.06
    ász
    -0.06
     coup
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.08
    -needed
    0.08
    ãģļãģ¤
    0.08
    å·¥ä½ľéľĢè¦ģ
    0.08
    à¸ĩาà¸Ļ
    0.08
     navÃŃc
    0.08
    精彩åĨħ容
    0.08
    æŁIJç§į
    0.08
    以åĨħçļĦ
    0.07
    /type
    0.07
    Activations Density 0.136%

    No Known Activations