© 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. 13670
    Prev
    Next
    INDEX
    Explanations

    Bar island names

    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
    å®ļä½į为
    -0.07
    ç¿°æŀĹ
    -0.07
    rar
    -0.06
    ä¸ĬæīĢ
    -0.06
    å½ĵæĤ¨
    -0.06
    éļıçĿĢæĪijåĽ½
    -0.06
    åįķè¾¹
    -0.06
    ione
    -0.06
    è¯ģåĪ¸æĬķèµĦ
    -0.06
    меÑģ
    -0.06
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.08
     survives
    0.08
     surviv
    0.08
    ç¹ģæ®ĸ
    0.08
    åŃĺæ´»
    0.08
    çĶĦ
    0.08
    ikel
    0.08
    ãĥ«ãĥ¼ãĥ«
    0.08
    åĺĢ
    0.08
    /rules
    0.08
    Activations Density 0.004%

    No Known Activations