© 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. 55646
    Prev
    Next
    INDEX
    Explanations

    departments and affiliations

    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
    大æīĵ
    -0.09
    mium
    -0.09
    滨海æĸ°åĮº
    -0.08
    çĶ±åİŁåijĬ
    -0.08
    cius
    -0.08
     Kha
    -0.08
    ftar
    -0.07
    ủ
    -0.07
    æĹ©çŁ¥éģĵ
    -0.07
    awns
    -0.07
    POSITIVE LOGITS
    主è¦ģä»İäºĭ
    0.08
    emeen
    0.07
     affiliated
    0.07
    contrib
    0.07
    aram
    0.07
    åĪĨéĥ¨
    0.07
     firstname
    0.07
     contribuer
    0.07
    artimento
    0.07
     Whip
    0.07
    Activations Density 0.160%

    No Known Activations