© 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. 56375
    Prev
    Next
    INDEX
    Explanations

    convert to another form

    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
    isman
    -0.08
    ะà¸Ļัà¹īà¸Ļ
    -0.07
    erk
    -0.07
    å°Ķçī¹
    -0.07
    onet
    -0.07
    -between
    -0.07
    znak
    -0.06
    esen
    -0.06
     tills
    -0.06
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    POSITIVE LOGITS
     into
    0.10
    转为
    0.09
    åĪ°è¿ĩ
    0.08
    åĪ°ä¸Ģ个
    0.08
    åĪ°å¤§
    0.08
    into
    0.08
    _into
    0.08
    lying
    0.08
    åĪ°ä»ĸ
    0.08
    åĪ°å°¾
    0.08
    Activations Density 0.025%

    No Known Activations