© 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. 27996
    Prev
    Next
    INDEX
    Explanations

    such as, for example

    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
     Zot
    -0.06
    ãģĹãĤĩ
    -0.06
    ï¸
    -0.06
     anden
    -0.06
    ï
    -0.06
    æĵİ
    -0.06
    (optional
    -0.06
    èĮĦ
    -0.06
    urtle
    -0.06
    kata
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.14
    æ¯Ķå¦Ĥ
    0.13
     напÑĢимеÑĢ
    0.13
    напÑĢимеÑĢ
    0.12
    ãģŁãģ¨ãģĪãģ°
    0.12
    æ¯Ķå¦Ĥåľ¨
    0.11
    诸å¦Ĥ
    0.11
    ä¾ĭãģĪãģ°
    0.10
     ÐĿапÑĢимеÑĢ
    0.10
     például
    0.10
    Activations Density 0.054%

    No Known Activations