© 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. 48243
    Prev
    Next
    INDEX
    Explanations

    technology and science concepts

    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
    æĸ¹åľĨ
    -0.08
    ALER
    -0.07
    itra
    -0.07
    orgen
    -0.07
    ä¸ĢåIJ¬
    -0.07
    沿éĿ©
    -0.07
     unless
    -0.07
    íĥĪ
    -0.06
    éĶĻè¿ĩçļĦ
    -0.06
    oran
    -0.06
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.07
    çŃīåİŁåĽł
    0.07
    çļĦ人æĿ¥è¯´
    0.07
    enc
    0.07
    èĤĸ
    0.07
    )))),
    0.07
    nas
    0.06
    å¹³çŃīçļĦ
    0.06
    )&&(
    0.06
     olmadıģı
    0.06
    Activations Density 0.485%

    No Known Activations