© 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. 21773
    Prev
    Next
    INDEX
    Explanations

    css prefix or js string keys

    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
    atable
    -0.07
    çĦ¶åIJİæł¹æį®
    -0.07
    ��
    -0.07
    iry
    -0.07
    å°ıåĪ°
    -0.07
    åĩĨåĪĻ
    -0.07
    ãģķãģĦ
    -0.07
    #/
    -0.06
    ���
    -0.06
    cae
    -0.06
    POSITIVE LOGITS
    inky
    0.08
    noinspection
    0.08
    uzz
    0.07
    uffix
    0.07
    åĭ¤åĭ¤æģ³æģ³
    0.07
    èĭ¦èĭ¦
    0.06
    vecs
    0.06
    esy
    0.06
    åĭĩå¾Ģ缴åīį
    0.06
    æ³ĽæĮĩ
    0.06
    Activations Density 0.001%

    No Known Activations