© 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. 21018
    Prev
    Next
    INDEX
    Explanations

    point through or around

    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
    åĴĮéĥ¨åĪĨ
    -0.07
    ä¸Ģ个好
    -0.07
    ä»İä¸Ģ个
    -0.06
     Parti
    -0.06
    allen
    -0.06
    stances
    -0.06
    ä¸Ģ群
    -0.06
     Cama
    -0.06
    ichtigen
    -0.06
    agina
    -0.06
    POSITIVE LOGITS
    Ùĩب
    0.08
    irected
    0.08
    ndo
    0.07
    èIJ±
    0.07
    ç³ł
    0.07
     directed
    0.07
    è¿İæĪĺ
    0.07
    à¸Ĺิศ
    0.07
    çĹħæĥħåĪĨæŀIJ
    0.07
    è¾Ł
    0.07
    Activations Density 0.001%

    No Known Activations