© 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. 45961
    Prev
    Next
    INDEX
    Explanations

    then ... returns

    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
    ä¸ĥ大
    -0.08
    éļıæŶ
    -0.08
    ibo
    -0.07
    hop
    -0.07
    ãģ°
    -0.07
    abah
    -0.07
    acias
    -0.07
    æĥħ
    -0.07
    èĩªæ²»
    -0.07
    illator
    -0.07
    POSITIVE LOGITS
     afterwards
    0.09
     thereafter
    0.08
    then
    0.07
     prem
    0.07
     ensuite
    0.07
     afterward
    0.07
    çĥ¨
    0.07
     subsequently
    0.07
     then
    0.07
    éĩľ
    0.07
    Activations Density 0.004%

    No Known Activations