© 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. 61150
    Prev
    Next
    INDEX
    Explanations

    drug detection dogs

    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
    AsString
    -0.07
    nds
    -0.07
    åĨ
    -0.07
    ounced
    -0.07
    ÑģÑĤÑĢÑĭ
    -0.07
    Titles
    -0.07
    relude
    -0.07
    èĭ¦å¿ĥ
    -0.07
    .FileSystem
    -0.07
    ennon
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļ次
    0.08
    åľ¨æľ¬æ¬¡
    0.07
    æĮ
    0.07
    æīĢ以å½ĵ
    0.06
    ale
    0.06
    åľ¨é¡¹çĽ®
    0.06
    å¯¹æľ¬æ¬¡
    0.06
    çĶ¨äºİ
    0.06
    istung
    0.06
    WG
    0.06
    Activations Density 0.538%

    No Known Activations