© 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. 23514
    Prev
    Next
    INDEX
    Explanations

    address followed by colon

    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
    ừng
    -0.08
     Gabin
    -0.07
    IGA
    -0.07
    ède
    -0.07
    ÑĢка
    -0.06
    ä¸ĩå²ģ
    -0.06
    undy
    -0.06
    леÑģо
    -0.06
    ukka
    -0.06
    ugas
    -0.06
    POSITIVE LOGITS
    æľīåħ³è¦ģæ±Ĥ
    0.07
    æľīäºĭ
    0.07
    vai
    0.07
    ÙĪ
    0.06
    оÑĤи
    0.06
    annie
    0.06
    ITCH
    0.06
    è®¤çľŁè´Łè´£
    0.06
    çĿĢéĩį
    0.06
    çī¹å°Ķ
    0.06
    Activations Density 0.002%

    No Known Activations