© 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. 48209
    Prev
    Next
    INDEX
    Explanations

    lists of recipients or members

    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
    azza
    -0.07
     **,
    -0.07
     respiro
    -0.07
    èĻı
    -0.07
    esso
    -0.07
    onato
    -0.07
    apon
    -0.07
    ugin
    -0.07
    çļĦä¸Ģç±»
    -0.07
    çļĦåİŁåĽłä¹ĭä¸Ģ
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.13
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.13
    代çłģå¦Ĥä¸ĭ
    0.12
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.11
    ):
    0.10
    以ä¸ĭæĺ¯
    0.10
    ä¾Ŀ次
    0.09
     list
    0.09
    ):-
    0.09
    }):
    0.09
    Activations Density 0.080%

    No Known Activations