© 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. 22801
    Prev
    Next
    INDEX
    Explanations

    lists about analysis

    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
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    ))-
    -0.07
    initely
    -0.07
    å½ĵçĦ¶è¦ģ
    -0.07
     definitely
    -0.07
     ÙħØ«ÙĦا
    -0.07
    ä¸ĭåĬŁå¤«
    -0.07
    acher
    -0.07
    å½ĵçĦ¶æĺ¯
    -0.07
    å¦Ĥæŀľè¯´
    -0.07
    POSITIVE LOGITS
    èĮ²
    0.08
    åħ¹
    0.08
    ĴĪ
    0.07
    Ø©
    0.07
    以ä¸ĭæŃ¥éª¤
    0.07
    ess
    0.07
    erst
    0.07
    dh
    0.07
    esse
    0.07
    åij±
    0.06
    Activations Density 0.006%

    No Known Activations