© 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. 63641
    Prev
    Next
    INDEX
    Explanations

    SDS and denaturation

    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
    scriber
    -0.07
    å±ģ
    -0.07
     Pickup
    -0.07
    ãng
    -0.07
    ihad
    -0.06
     Futsal
    -0.06
    çĶļå°ij
    -0.06
     bassin
    -0.06
    èĹıçĿĢ
    -0.06
    åĺ¹
    -0.06
    POSITIVE LOGITS
    çł´åĿı
    0.09
    çł´åĿıäºĨ
    0.09
    é«ĺ温
    0.08
     irreversible
    0.08
     destruction
    0.08
     damage
    0.08
     destroy
    0.07
    æij§æ¯ģ
    0.07
    æ¯ģçģŃ
    0.07
    åºĶæ¿Ģ
    0.07
    Activations Density 0.048%

    No Known Activations