© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20568
    Prev
    Next
    INDEX
    Explanations

    namespace declarations

    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
    ustru
    -0.08
    ilight
    -0.08
    è¿ħ
    -0.08
    ascar
    -0.08
    ,module
    -0.07
    LEGAL
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
    ifat
    -0.07
    ½
    -0.07
    åłĤåłĤ
    -0.07
    POSITIVE LOGITS
    à¸ķัว
    0.06
    æĥ«
    0.06
    év
    0.06
    ech
    0.06
    ä¸į大çļĦ
    0.06
    å¤ļçĤ¹
    0.06
     Buen
    0.05
    ä¸ĢèĪ¬æĿ¥è¯´
    0.05
    æģĻ
    0.05
    åµĮ
    0.05
    Activations Density 0.006%

    No Known Activations