© 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. 8477
    Prev
    Next
    INDEX
    Explanations

    describing a process or method

    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
    poon
    -0.08
    eltu
    -0.08
    æ¸ħè¿ľ
    -0.08
    tourn
    -0.08
    eggi
    -0.08
    ÅĤek
    -0.07
    owitz
    -0.07
    acol
    -0.07
    _TW
    -0.07
    湿äºĨ
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæŃ¥éª¤
    0.08
     firstly
    0.07
    åħĪå°Ĩ
    0.07
    usher
    0.07
    伯
    0.07
    åīįåħĪ
    0.07
    çŃīå¥ĸ
    0.06
    éĺħ读åİŁæĸĩ
    0.06
    ä¸Ģæĺ¯
    0.06
    两ç§įæĸ¹å¼ı
    0.06
    Activations Density 0.018%

    No Known Activations