© 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. 28941
    Prev
    Next
    INDEX
    Explanations

    endangered, threatened, extinction, survival

    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
    ornado
    -0.08
    ulun
    -0.07
    çķ¥å¸¦
    -0.06
     dét
    -0.06
    -pic
    -0.06
    -direction
    -0.06
    è¡Įæĸĩ
    -0.06
     Magnum
    -0.06
    äºij顶
    -0.06
     pia
    -0.06
    POSITIVE LOGITS
    æ¿Ĵåį±
    0.14
    çģŃç»Ŀ
    0.14
     endangered
    0.11
     threatened
    0.11
     extinct
    0.10
    èĦĨå¼±
    0.10
     threats
    0.10
    frag
    0.10
     иÑģÑĩеза
    0.10
     extinction
    0.10
    Activations Density 0.066%

    No Known Activations