© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    example text or sample

    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
    æ²¾æŁĵ
    -0.07
    kü
    -0.06
    anship
    -0.06
    ampu
    -0.06
    lix
    -0.06
    ünsch
    -0.06
    ä¸įéĢĤ
    -0.06
     kac
    -0.06
     unequiv
    -0.06
     permanently
    -0.06
    POSITIVE LOGITS
    éŀł
    0.08
    obil
    0.08
    gage
    0.08
    ((__
    0.08
    semble
    0.08
    帮åĬ©æĪij们
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹
    0.07
    veal
    0.07
    å°Ĩè¿Ļ
    0.07
     recours
    0.07
    Activations Density 0.001%

    No Known Activations