© 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. 56778
    Prev
    Next
    INDEX
    Explanations

    roof, minutes, one, slow, 5, it, can

    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
    appings
    -0.09
    cii
    -0.08
    ×ķת
    -0.08
    ÙĦÙĪد
    -0.08
    eway
    -0.08
    _subnet
    -0.07
    äºĴ帮
    -0.07
    ibal
    -0.07
    uilder
    -0.07
    alias
    -0.07
    POSITIVE LOGITS
     nonexistent
    0.10
    ä¸Ķä¸į
    0.09
    æŀģ
    0.09
    æŀģ为
    0.09
    èĢĮä¸Ķ
    0.09
    èĢĮä¸Ķè¦ģ
    0.09
    æŀģåħ¶
    0.09
    èĢĮä¸Ķæĺ¯
    0.08
     voire
    0.08
    çĶļèĩ³
    0.08
    Activations Density 0.210%

    No Known Activations