© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    cost, consumption, impact, estimated

    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
    spra
    -0.08
    转载æĪĸå¼ķçĶ¨
    -0.08
    μÏİν
    -0.08
    -anchor
    -0.07
    æĦĪåĬł
    -0.07
    ultipart
    -0.07
    æ¬²æľĽ
    -0.07
    -bordered
    -0.07
    tridge
    -0.07
    ablemente
    -0.07
    POSITIVE LOGITS
     Assuming
    0.08
    åģĩ设
    0.08
     assuming
    0.08
    ä¼°ç®Ĺ
    0.07
     assume
    0.07
     estimated
    0.07
    æĥĬ人
    0.07
     conceivable
    0.07
    ä¾µ
    0.07
     feas
    0.07
    Activations Density 0.029%

    No Known Activations