© 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. 19369
    Prev
    Next
    INDEX
    Explanations

    apparatus, library, unattended, shell, communication, safety, micro

    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
    åħ¼
    -0.07
    æ¦Ķ
    -0.06
    nikov
    -0.06
    åħ¼ãģŃ
    -0.06
    ä¸įä¸Ĭ
    -0.06
     V
    -0.06
    èij
    -0.06
    deel
    -0.05
     E
    -0.05
    tein
    -0.05
    POSITIVE LOGITS
    诸å¦Ĥ
    0.19
    æ¯Ķå¦Ĥ
    0.11
    ä¾ĭå¦Ĥ
    0.11
    èѬå¦Ĥ
    0.11
    ãģŁãģ¨ãģĪãģ°
    0.10
    æ¯Ķå¦Ĥåľ¨
    0.10
     вÑĢоде
    0.10
    ä¾ĭãģĪãģ°
    0.10
     à¸Ńาà¸Ĺิ
    0.10
    èijĹåIJįçļĦ
    0.10
    Activations Density 0.156%

    No Known Activations