© 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. 46783
    Prev
    Next
    INDEX
    Explanations

    personal privacy rights

    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
    ัà¸Ļ
    -0.09
    æĥķ
    -0.07
    çĸµ
    -0.07
     bando
    -0.07
    æŃ¥æŃ¥é«ĺ
    -0.07
    以å¾ħ
    -0.07
    öhn
    -0.07
    ÑģÑĤин
    -0.07
     hal
    -0.07
     Kota
    -0.07
    POSITIVE LOGITS
     prer
    0.11
    å¹²æ¶ī
    0.10
    æıĴæīĭ
    0.10
    åºĶçĶ±
    0.10
    ä¸īå°º
    0.09
     meddling
    0.09
     domain
    0.09
     autonomy
    0.08
    é¢ĨåŁŁ
    0.08
     inger
    0.08
    Activations Density 0.056%

    No Known Activations