© 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. 38878
    Prev
    Next
    INDEX
    Explanations

    phone number, address

    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
    -0.07
    è¿Ļ对äºİ
    -0.07
    ails
    -0.07
    è¿Ļè¯Ŀ
    -0.06
    è¿Ļä¸ĢçĤ¹
    -0.06
    è¿ĻçĤ¹
    -0.06
    .k
    -0.06
    Ø·
    -0.06
    è¿Ļæĺ¯
    -0.06
    t
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.13
    ardt
    0.08
    è¦ģä¹Ī
    0.08
    JNI
    0.08
    ãĥ¼ãĤº
    0.08
    ä¸Ģè¦ģ
    0.08
    epro
    0.08
    ìŀĺ
    0.08
    ONS
    0.07
    ledes
    0.07
    Activations Density 0.065%

    No Known Activations