© 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. 40716
    Prev
    Next
    INDEX
    Explanations

    over/underestimation

    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
    æĸ°å¤©åľ°
    -0.07
    ìĩł
    -0.07
    ä¹ĭä¸ī
    -0.07
    ullet
    -0.07
    пада
    -0.07
    ä¸Ńæļij
    -0.07
    èIJ½ä¸ĭ
    -0.07
    çĶ±å¸Ĥ
    -0.07
    ilde
    -0.07
    agy
    -0.06
    POSITIVE LOGITS
    ä½İä¼°
    0.09
    ervo
    0.08
    /false
    0.08
    æĤł
    0.07
    ä¼°
    0.07
    arend
    0.07
    linger
    0.07
     зани
    0.07
    å°¤åħ¶æĺ¯åľ¨
    0.07
     raf
    0.07
    Activations Density 0.049%

    No Known Activations