© 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. 60934
    Prev
    Next
    INDEX
    Explanations

    confiscate, expel, commission, justice, ban, allow

    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
    ä¹ħèĢĮä¹ħä¹ĭ
    -0.08
     ëķĮ문ìĿ´ëĭ¤
    -0.08
    inkt
    -0.08
    缩éĩı
    -0.08
    agd
    -0.07
    ä¸Ģ次åıĪä¸Ģ次
    -0.07
     terecht
    -0.07
    afil
    -0.07
    æľĢåIJİä¸Ģåħ¬éĩĮ
    -0.07
    夯
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¾ĭ
    0.11
    åį³æĹ¥èµ·
    0.10
    æ°¸ä¹ħ
    0.09
    æ°¸ä¹ħæĢ§
    0.08
     unlimited
    0.08
     unprecedented
    0.08
     künftig
    0.08
     unspecified
    0.08
    æīĢæľī
    0.08
    æīĢæľīçļĦ
    0.08
    Activations Density 0.199%

    No Known Activations