© 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. 63485
    Prev
    Next
    INDEX
    Explanations

    sequence or next event

    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
    çµIJãģ³
    -0.08
    å±ĬæŶ
    -0.07
    agnost
    -0.07
    ubber
    -0.07
    ira
    -0.07
    غاÙĨ
    -0.07
    akwa
    -0.06
    åĪĹå¸Ń
    -0.06
     ranger
    -0.06
    æĹ©é¤IJåIJİ
    -0.06
    POSITIVE LOGITS
    å°ijéĩıçļĦ
    0.07
    ç¥ł
    0.07
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.07
    adays
    0.07
     subsequent
    0.06
    allet
    0.06
    è¹Ī
    0.06
     dilanjutkan
    0.06
    çĶ¸
    0.06
    åħ¶å®ĥ
    0.06
    Activations Density 0.036%

    No Known Activations