© 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. 41248
    Prev
    Next
    INDEX
    Explanations

    unit or zero

    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
    ontage
    -0.08
    SEQUENTIAL
    -0.07
    stery
    -0.07
    ippy
    -0.07
    PLEX
    -0.07
    }@
    -0.07
    æĪij们身边
    -0.07
    izei
    -0.07
    åıįè¿ĩæĿ¥
    -0.07
    山海
    -0.07
    POSITIVE LOGITS
    ä¸İä¼Ĺ
    0.09
    åĴĮå¹³
    0.08
    å±ħ
    0.08
    åĴĮ第äºĮ
    0.07
     peacefully
    0.07
    å¹³åĿĩåĢ¼
    0.07
    ayer
    0.07
    çĭ¬
    0.07
    第ä¸Ģ项
    0.07
    usta
    0.07
    Activations Density 0.002%

    No Known Activations