© 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. 11662
    Prev
    Next
    INDEX
    Explanations

    `and` or `,` following certain words

    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
    .remaining
    -0.07
    ỳ
    -0.07
    å°±æĺ¯è¿Ļ个
    -0.06
     поним
    -0.06
    å°±æĺ¯æĪij
    -0.06
     understanding
    -0.06
    ients
    -0.06
    anaan
    -0.06
    ~
    -0.06
    ÃŃas
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.13
    è¿ĻäºĽéĥ½
    0.10
    —all
    0.10
    è¿Ļéĥ½æĺ¯
    0.09
    åĿĩå±ŀ
    0.09
    éĥ½å±ŀäºİ
    0.08
    imi
    0.08
    ãģ©ãĤĮãĤĤ
    0.08
    å±ŀäºİ
    0.08
    ThanOr
    0.07
    Activations Density 0.004%

    No Known Activations