© 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. 46762
    Prev
    Next
    INDEX
    Explanations

    mySQL

    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
    ?key
    -0.07
    issan
    -0.06
    满åłĤ
    -0.06
    çī¹éķ¿çĶŁ
    -0.06
     небе
    -0.06
    éŁ
    -0.06
    hren
    -0.06
    Bearer
    -0.06
    _ELEM
    -0.06
    èµĦæĸĻä¸ĭè½½
    -0.06
    POSITIVE LOGITS
    æİī
    0.07
     Rodrig
    0.07
    åĩºä¸į
    0.07
    mist
    0.07
    awk
    0.07
    unki
    0.07
    å¿ĺè®°
    0.06
    коÑĤа
    0.06
    à°Ĥà°ļ
    0.06
    åłµ
    0.06
    Activations Density 0.001%

    No Known Activations