© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12098
    Prev
    Next
    INDEX
    Explanations

    why/way questions

    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
    abad
    -0.08
    å¾Īå¤ļéĹ®é¢ĺ
    -0.08
    emps
    -0.08
    并æĹł
    -0.07
    phis
    -0.07
    ä¹Łå¤ļ
    -0.07
    inna
    -0.07
    ÅĤu
    -0.07
    ance
    -0.07
    ptest
    -0.07
    POSITIVE LOGITS
    å¿ĹæĪIJ
    0.07
     Ke
    0.07
    ython
    0.06
    °
    0.06
     /.
    0.06
    Ke
    0.06
     ().
    0.06
    éģĵéģĵ
    0.06
    ke
    0.06
    acher
    0.06
    Activations Density 0.033%

    No Known Activations