© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    development or former

    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
    çĭ°
    -0.07
    cente
    -0.07
    çĦ¡çIJĨ
    -0.07
    боÑİ
    -0.07
    etid
    -0.07
    空æ°Ķ
    -0.07
    iaus
    -0.07
    åį°ç¬¬
    -0.07
    ĤŃ
    -0.07
     POSSIBILITY
    -0.07
    POSITIVE LOGITS
    åıĬéĥ¨åĪĨ
    0.10
    åĴĮéĥ¨åĪĨ
    0.10
    æľīä½Ļ
    0.08
    èĢĮä¸įè§ģ
    0.07
    ãģłãģijãģ¯
    0.07
    æ¯Ķè¾ĥ容æĺĵ
    0.07
    没éĹ®é¢ĺ
    0.07
    uku
    0.07
    andar
    0.07
    oll
    0.07
    Activations Density 0.321%

    No Known Activations