© 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. 39713
    Prev
    Next
    INDEX
    Explanations

    describing paths and directions

    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
    åĥıä½ł
    -0.07
    è¡Ĺ头
    -0.07
    è¿ľåľ¨
    -0.07
    å±±å·Ŀ
    -0.06
    åĨ°å±±
    -0.06
    æ±Łæ²³
    -0.06
    浴缸
    -0.06
    éĢĥéĢ¸
    -0.06
    ync
    -0.06
    éķ¿ç©º
    -0.06
    POSITIVE LOGITS
    åħ¥åı£
    0.11
    å¿ħç»ı
    0.10
    尽头
    0.09
    éģ¿å¼Ģ
    0.09
    è·¯å¾Ħ
    0.09
    éĢļå¾Ģ
    0.08
    æ¡ĪåĨħ
    0.08
     menuju
    0.08
    åľ°åĬ¿
    0.08
     pathway
    0.08
    Activations Density 0.200%

    No Known Activations