© 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. 31635
    Prev
    Next
    INDEX
    Explanations

    academic and professional contexts

    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
    ikle
    -0.06
    æĿī
    -0.06
    headed
    -0.06
    缴
    -0.06
    leos
    -0.06
    esser
    -0.06
    StyleSheet
    -0.06
    椿
    -0.06
    åijij
    -0.06
    kové
    -0.06
    POSITIVE LOGITS
    çģĮ注
    0.08
    epend
    0.08
    éĢĤ
    0.08
    ä»İä½ķ
    0.07
    æ¶Įçİ°
    0.07
    è§ģå¾Ĺ
    0.07
    ammt
    0.07
    åĨįæĢİä¹Ī
    0.07
    为ä¹ĭ
    0.07
    éħµ
    0.07
    Activations Density 0.021%

    No Known Activations