© 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. 13358
    Prev
    Next
    INDEX
    Explanations

    capturing, embedding, placeholder, submit, lending

    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
    æľĢä¸į
    -0.07
    主è¦ģ表çݰ为
    -0.07
    åĽŀå¸ĸ
    -0.07
    opf
    -0.07
    è¿ľç¦»
    -0.07
    è¿ĺæľī许å¤ļ
    -0.07
    åĽŀ头
    -0.06
     prej
    -0.06
    istr
    -0.06
    illers
    -0.06
    POSITIVE LOGITS
    ä¸ĢäºĽéĹ®é¢ĺ
    0.08
    quotes
    0.07
     placeholder
    0.07
    asst
    0.07
    _compile
    0.07
    æĺ¯ä¸ĢäºĽ
    0.07
    åĭī
    0.07
    ä¸ĢäºĽ
    0.07
     placeholders
    0.07
    å¹³åİ¿
    0.07
    Activations Density 0.003%

    No Known Activations