© 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. 16974
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact info

    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
    è¦ģä¿Ŀè¯ģ
    -0.07
    ä¸įæĶ¶
    -0.06
    æŀģ
    -0.06
    anvas
    -0.06
    llib
    -0.06
     Cian
    -0.06
    velt
    -0.06
    è¾½éĺĶ
    -0.06
    alli
    -0.06
    åĥıä½ł
    -0.06
    POSITIVE LOGITS
    ç¬ij声
    0.08
    缴éĢļ
    0.07
    åij¨ä¸Ģèĩ³
    0.07
     call
    0.07
    èIJĿèİī
    0.07
    call
    0.07
     siège
    0.07
    /+
    0.07
    -call
    0.07
    idian
    0.07
    Activations Density 0.088%

    No Known Activations