© 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. 61038
    Prev
    Next
    INDEX
    Explanations

    directional locations

    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
    uluk
    -0.07
     cứ
    -0.07
    éľ²æ°´
    -0.07
    对被
    -0.07
    è¿Ŀ
    -0.07
    åĮºåĮº
    -0.07
    ÙĴÙĥ
    -0.07
    æ¶ī
    -0.07
    compiler
    -0.07
    adat
    -0.07
    POSITIVE LOGITS
    зÑı
    0.07
    oval
    0.07
    æĥ£
    0.06
    èİ
    0.06
    çĶ»æ³ķ
    0.06
    æĿ±è¥¿
    0.06
    ingend
    0.06
    thur
    0.06
    _gid
    0.06
    ä¸ľè¥¿
    0.06
    Activations Density 0.002%

    No Known Activations