© 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. 18519
    Prev
    Next
    INDEX
    Explanations

    archives and historical terms

    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
    æľīä¸ĭåĪĹ
    -0.08
    åħ·æľī以ä¸ĭ
    -0.08
    主è¦ģæľī
    -0.07
    æľī以ä¸ĭ
    -0.07
    æ»ij
    -0.06
    æ´»
    -0.06
    ì±ħ
    -0.06
    :\\
    -0.06
    .Microsoft
    -0.06
    主è¦ģåĪĨ为
    -0.06
    POSITIVE LOGITS
     versus
    0.10
     vs
    0.10
    nip
    0.08
     mentioned
    0.08
    ãģ®è©±
    0.08
    ä¾Ľå¤§å®¶åıĤèĢĥ
    0.08
    vs
    0.08
     mention
    0.08
    çļĦåı¯èĥ½æĢ§
    0.08
     erwäh
    0.08
    Activations Density 0.031%

    No Known Activations