© 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. 9962
    Prev
    Next
    INDEX
    Explanations

    code ethics, Official Capacities, sexuality

    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
    ä¸Ĭæľī
    -0.07
    igate
    -0.07
    ↵
    -0.07
     on
    -0.06
    ¤
    -0.06
    pod
    -0.06
    ä¸ĬçļĦ
    -0.06
    éĺ¿
    -0.06
     -
    -0.06
    åľŁè±ª
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    пам
    0.07
    etheless
    0.07
    身临åħ¶å¢ĥ
    0.07
    wiad
    0.07
    è·ĥè·ĥ欲è¯ķ
    0.07
    åIJĥåIJĥ
    0.07
    JD
    0.07
    åĬĽè¡Į
    0.07
    Activations Density 0.098%

    No Known Activations