© 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. 17673
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by comma or number

    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
    IDAS
    -0.08
    levance
    -0.07
    绿èī²åıijå±ķ
    -0.07
    itto
    -0.07
    פ×ķר
    -0.06
    é¾Ļæ¹¾
    -0.06
    çĥ¦
    -0.06
     Heidel
    -0.06
    è¶ħéĢŁ
    -0.06
    emn
    -0.06
    POSITIVE LOGITS
     Raw
    0.07
    幸
    0.07
    ruit
    0.07
    æĶ¯çĤ¹
    0.06
    ä¸įèĩ³äºİ
    0.06
     intit
    0.06
    raca
    0.06
    sand
    0.06
     manifest
    0.06
    .jquery
    0.06
    Activations Density 0.069%

    No Known Activations