© 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. 30690
    Prev
    Next
    INDEX
    Explanations

    indicates

    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
    oose
    -0.07
    éķIJ
    -0.07
    atorio
    -0.06
    æĬ
    -0.06
     Dmit
    -0.06
    aney
    -0.06
    kn
    -0.06
    ono
    -0.06
    å®ī
    -0.06
    china
    -0.06
    POSITIVE LOGITS
     âĶľâĶĢâĶĢ
    0.08
    inium
    0.08
    initi
    0.07
    licit
    0.07
    çļĦæ¯ıä¸Ģ
    0.07
    çĤ¹æѤ
    0.07
    ä¼Ĭå§ĭ
    0.07
    以ä¸ĭ为
    0.07
    è¾ĽåĬ³
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    Activations Density 0.117%

    No Known Activations