© 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. 26265
    Prev
    Next
    INDEX
    Explanations

    mathematical variable assignments

    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
    ubi
    -0.08
    _ALLOW
    -0.08
    ä¸Ĭ人
    -0.08
    请æĮī
    -0.07
    çİĩè¾¾
    -0.07
    ingo
    -0.07
    riz
    -0.07
    çļĦéĤ£ç§į
    -0.07
    plode
    -0.07
    otte
    -0.07
    POSITIVE LOGITS
    åĪ«
    0.07
    atis
    0.07
    wright
    0.06
    keur
    0.06
    anden
    0.06
    aret
    0.06
    æĹ¥çĶµ
    0.06
    ytt
    0.06
     cre
    0.06
    WithOptions
    0.06
    Activations Density 0.005%

    No Known Activations