© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21803
    Prev
    Next
    INDEX
    Explanations

    midwife, NULL, canvas, ribosomes, pH, driver, login

    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
    icanos
    -0.08
    åħ·ä½ĵæŶéĹ´
    -0.07
    éļıçĿĢæŶéĹ´çļĦ
    -0.07
    iecz
    -0.07
    åħ·ä½ĵæĥħåĨµ
    -0.07
    غب
    -0.07
     ÃĤn
    -0.07
    pire
    -0.07
    psc
    -0.07
    _UNITS
    -0.07
    POSITIVE LOGITS
    项
    0.07
    æ··æ·Ĩ
    0.06
    ä¸Ń转
    0.06
    æł¹æľ¬å°±æ²¡æľī
    0.06
    éĺģ
    0.06
    åįĥä¸ĩä¸įèĥ½
    0.06
     ked
    0.06
    ä¸İæľ¬
    0.06
     contr
    0.06
     concern
    0.06
    Activations Density 0.003%

    No Known Activations