© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2510
    Prev
    Next
    INDEX
    Explanations

    "my VL and tcells"

    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
    ï
    -0.07
    Ñĸй
    -0.07
    ús
    -0.07
     McB
    -0.07
    ã
    -0.06
    ijo
    -0.06
    ç¥Ŀè´º
    -0.06
     Mã
    -0.06
    î
    -0.06
    adium
    -0.06
    POSITIVE LOGITS
    åĴĮåħ¶å®ĥéĹ®é¢ĺ
    0.09
    åĿIJè¯Ĭ
    0.09
    åĭĩå¾Ģ缴åīį
    0.08
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    0.08
    æĸ°åĬłåĿ¡
    0.08
    èĢĮèµ°
    0.08
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    0.08
    efois
    0.08
    ä¸Ģå¤ķ
    0.08
    äºĨ好
    0.07
    Activations Density 0.130%

    No Known Activations