© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    placeholders and programming syntax

    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
    onne
    -0.07
    ей
    -0.07
    ¶
    -0.07
    åŁ¹åħ»å¹¼åĦ¿
    -0.06
    é»ĦéħĴ
    -0.06
    æ°ijæĶ¿éĥ¨
    -0.06
    loge
    -0.06
    æݨåĩºçļĦ
    -0.06
    çľĭåĽ¾
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    POSITIVE LOGITS
    shire
    0.08
    èĢ½
    0.08
    ì§ľ
    0.08
    ä¸Ģè¯ķ
    0.08
    ỡ
    0.07
    cano
    0.07
    ä¹ĥ
    0.07
    èİİæĭī
    0.07
    éĹ®åĮ»çĶŁ
    0.07
    reat
    0.07
    Activations Density 0.003%

    No Known Activations