© 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. 40042
    Prev
    Next
    INDEX
    Explanations

    scripting tasks for software

    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
     tslint
    -0.07
    cred
    -0.07
    arne
    -0.07
    æļ§
    -0.06
    åıªåı¯æĥľ
    -0.06
    ç¾İä¸įèĥľæĶ¶
    -0.06
     Stanford
    -0.06
    lord
    -0.06
    جÙĬÙĦ
    -0.06
    amen
    -0.06
    POSITIVE LOGITS
     Pian
    0.07
    DER
    0.07
    fore
    0.07
    èĪ
    0.06
    ãĥĢãĥ¼
    0.06
     tasks
    0.06
    泡
    0.06
    ä¸įç´Ĭ
    0.06
     Gle
    0.06
    assis
    0.06
    Activations Density 0.011%

    No Known Activations