© 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. 41759
    Prev
    Next
    INDEX
    Explanations

    "quoted words"

    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
    lement
    -0.08
    istu
    -0.07
    orem
    -0.06
    缸åħ³èµĦæĸĻ
    -0.06
     impi
    -0.06
    ç»Ŀåľ°
    -0.06
    asionally
    -0.06
    ponent
    -0.06
    æĨ§æĨ¬
    -0.06
    øb
    -0.06
    POSITIVE LOGITS
    åIJİæĦŁ
    0.08
    åij½çļĦ
    0.07
    *”
    0.07
     existi
    0.07
    è°ģæĿ¥
    0.07
    çľĭä¸įè§ģ
    0.07
    çIJĥ迷们
    0.07
    æĬĵ
    0.07
    åĩıæ³ķ
    0.07
    **”
    0.07
    Activations Density 0.036%

    No Known Activations