© 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. 19644
    Prev
    Next
    INDEX
    Explanations

    occupied territories

    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¸Ģæī«
    -0.07
    ä¸İçݯå¢ĥ
    -0.06
    omod
    -0.06
    大åĪ°
    -0.06
    /group
    -0.06
    è´´è¿ij
    -0.06
    imax
    -0.06
    åıijæķ£
    -0.06
     guild
    -0.06
    注æĦıçļĦæĺ¯
    -0.06
    POSITIVE LOGITS
    åįķæĸ¹éĿ¢
    0.11
     disputed
    0.11
    äºī端
    0.09
    åĥµå±Ģ
    0.09
     unilateral
    0.08
    åįķè¾¹
    0.08
     rivend
    0.08
    å½ĵå±Ģ
    0.08
     peacefully
    0.08
     sovereignty
    0.08
    Activations Density 0.148%

    No Known Activations