© 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. 8510
    Prev
    Next
    INDEX
    Explanations

    advice and corrections

    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
    ä¼ij
    -0.07
    ardini
    -0.07
    è¿Ľä¸ĢæŃ¥åĬłå¼º
    -0.07
    æľĢæĸ°
    -0.06
    缮
    -0.06
    ä¸įå¿ħ
    -0.06
    便åĪ©
    -0.06
    ä¹į
    -0.06
    agon
    -0.06
    ä¸įçĶ¨åĨį
    -0.06
    POSITIVE LOGITS
    æīį对
    0.14
    æīįè¡Į
    0.14
    è¿Ļæīįæĺ¯
    0.11
    æīįèĥ½çľŁæŃ£
    0.11
    åıĸèĢĮ代ä¹ĭ
    0.10
    æīįæĺ¯
    0.10
     instead
    0.10
    æĶ¹çĤº
    0.10
    æīį好
    0.10
     dagegen
    0.09
    Activations Density 0.183%

    No Known Activations