© 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. 4349
    Prev
    Next
    INDEX
    Explanations

    both/two groups/tests/sentences/theories

    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
    å°±è¿Ļä¹Ī
    -0.07
    COOKIE
    -0.07
    anh
    -0.07
     Pon
    -0.07
    ä¸ĢéŨ
    -0.07
    ERO
    -0.06
    CHI
    -0.06
     MÃł
    -0.06
    ampton
    -0.06
    çĶŁæ´»ä¹łæĥ¯
    -0.06
    POSITIVE LOGITS
    ä½Ļåħī
    0.07
    çĸ½
    0.07
    .pixel
    0.07
     uff
    0.07
    vester
    0.07
     treasure
    0.07
    å±ij
    0.07
    å¾Ĺ天
    0.07
    以èĩ³
    0.07
    ikus
    0.07
    Activations Density 0.001%

    No Known Activations