© 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. 32088
    Prev
    Next
    INDEX
    Explanations

    chunk counter

    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
     tw
    -0.08
    年第
    -0.06
    çĽij
    -0.06
     penny
    -0.06
    ieg
    -0.06
    tw
    -0.06
    ä»İè½»
    -0.06
    èıģ
    -0.06
    çº
    -0.06
    çī¹åħ¸
    -0.06
    POSITIVE LOGITS
     chunk
    0.10
    chunk
    0.10
    Chunk
    0.10
    ä¸Ģæ°Ĺãģ«
    0.09
    ä¸Ģ次æĢ§
    0.09
     Chunk
    0.09
    æī¹éĩı
    0.09
    è¿Ļä¸Ģ段
    0.09
    remaining
    0.09
    _chunk
    0.08
    Activations Density 0.049%

    No Known Activations