© 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. 57034
    Prev
    Next
    INDEX
    Explanations

    is designed

    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
    åıijå±ķæĸ°
    -0.08
     sosialis
    -0.07
    denes
    -0.07
    èī²åĪĹ
    -0.07
    resh
    -0.07
     getch
    -0.07
    urez
    -0.07
    éļIJ
    -0.07
    irate
    -0.07
    çļĦéĺ¶æ®µ
    -0.07
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.08
     hingegen
    0.07
    ãģĵãģ¡ãĤīãģ¯
    0.07
    åį´åĽłä¸º
    0.07
     наобоÑĢоÑĤ
    0.07
    éns
    0.07
     напÑĢоÑĤив
    0.07
     natomiast
    0.07
    åĪĻ以
    0.07
    æıIJä¾ĽäºĨä¸Ģ个
    0.07
    Activations Density 0.001%

    No Known Activations