© 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. 32116
    Prev
    Next
    INDEX
    Explanations

    mediators, growth factor, RNA, flying, CT

    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
    emers
    -0.08
    è¯ģå®ŀåħ¶
    -0.08
     మరి
    -0.08
    使å®ĥ
    -0.07
    ryp
    -0.07
    缸åħ³æĸ°éĹ»
    -0.07
    irman
    -0.07
    导读
    -0.07
     Dau
    -0.07
    微信æī«çłģ
    -0.07
    POSITIVE LOGITS
    osis
    0.07
    çĩ
    0.07
    .Roles
    0.06
    å°Ĩèİ·å¾Ĺ
    0.06
    agle
    0.06
    æĸ
    0.06
    ody
    0.05
    «
    0.05
    itled
    0.05
    uspend
    0.05
    Activations Density 0.004%

    No Known Activations