© 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. 18425
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ÙĬرة
    -0.08
    åĩºè´¨
    -0.07
    saf
    -0.07
    kirchen
    -0.07
     Horton
    -0.07
     thế
    -0.07
    åı¯èĥ½ä¼ļåĩºçİ°
    -0.07
    åıĮåŁİ
    -0.07
    å¼±çĶµ
    -0.06
     ÃŃn
    -0.06
    POSITIVE LOGITS
    seek
    0.08
    å¿ĥä¸Ńæľī
    0.07
     misrepresented
    0.07
    ìĬ¹
    0.07
     somehow
    0.07
    çĶļæĺ¯
    0.07
    å¹²èĦĨ
    0.07
     particul
    0.07
    åı£å¾Ħ
    0.06
    éĤĥ
    0.06
    Activations Density 0.044%

    No Known Activations