© 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. 14678
    Prev
    Next
    INDEX
    Explanations

    mapping to another

    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
    ura
    -0.07
    koch
    -0.06
    对ä¸Ĭè¿°
    -0.06
    pare
    -0.06
    缴è¾ĸå¸Ĥ
    -0.06
    ÅĤoÅĽ
    -0.06
    otes
    -0.06
    é¦ĸ
    -0.06
    inst
    -0.05
    NEL
    -0.05
    POSITIVE LOGITS
     corresponding
    0.12
     ones
    0.11
    ãģĿãģĨãģ§
    0.11
     altrett
    0.11
     hers
    0.10
    çĽ¸å¯¹åºĶçļĦ
    0.10
     ê·¸ëłĩì§Ģ
    0.10
    ä¸İä¹ĭ
    0.10
     altrettanto
    0.09
    缸åºĶçļĦ
    0.09
    Activations Density 0.298%

    No Known Activations