© 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. 7610
    Prev
    Next
    INDEX
    Explanations

    asking for or needing

    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
    åĩ¡äºĭ
    -0.08
     luckily
    -0.08
    odle
    -0.08
    sius
    -0.07
     excelentes
    -0.07
    мили
    -0.07
    åĿıäºĭ
    -0.07
    _MAGIC
    -0.07
    -Mart
    -0.07
    äºĭå®ŀè¯ģæĺİ
    -0.07
    POSITIVE LOGITS
     underlying
    0.11
    éļIJåIJ«
    0.11
    æ·±å±Ĥ
    0.10
     probably
    0.09
    å®ŀéĻħéľĢæ±Ĥ
    0.09
    æ¸´æľĽ
    0.09
    éļIJèĹıçĿĢ
    0.09
    æĺ¯æĥ³
    0.09
    çŁ¥ãĤĬãģŁãģĦ
    0.08
     implicit
    0.08
    Activations Density 0.038%

    No Known Activations