© 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. 29821
    Prev
    Next
    INDEX
    Explanations

    words and phrases

    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
    ($("#
    -0.07
    \base
    -0.06
    ä¸ĬåĽ¾
    -0.06
    æ·±åħ¥æµħ
    -0.06
    iped
    -0.06
    åĿŁ
    -0.06
    iggins
    -0.06
     minh
    -0.06
    IMUM
    -0.06
    æµ®åĬ¨
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.15
     phrases
    0.14
    è¯Ńåı¥
    0.11
    çĶ¨è¯Ń
    0.11
     descriptors
    0.11
     phrase
    0.10
     statements
    0.10
     verbs
    0.10
    ï¼ļ“
    0.10
    åŃĹçľ¼
    0.09
    Activations Density 0.081%

    No Known Activations