© 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. 47835
    Prev
    Next
    INDEX
    Explanations

    dopaminergic function and uptake

    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
    èĩªèº«
    -0.07
    æľ¬èº«
    -0.07
     underlying
    -0.07
    å³ł
    -0.07
    æŶéĹ´åľ¨
    -0.07
    ãģ¶ãĤĬ
    -0.07
    åľ¨ç©ºä¸Ń
    -0.07
    åīįèĢħ
    -0.07
    åŃĺåľ¨äºİ
    -0.06
    è¿ĩç¨ĭä¸ŃçļĦ
    -0.06
    POSITIVE LOGITS
    athers
    0.08
    ught
    0.08
    åĴĮåIJİ
    0.07
    oo
    0.07
    ç±³å¤Ħ
    0.07
    请çĻ»å½ķ
    0.07
    antics
    0.07
    ifer
    0.07
    åĨįçĶ±
    0.07
    ieg
    0.06
    Activations Density 1.044%

    No Known Activations