© 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. 18287
    Prev
    Next
    INDEX
    Explanations

    here is

    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
    ahun
    -0.08
    Õ¶
    -0.07
    åľ¨
    -0.07
    ome
    -0.07
    åħ®
    -0.07
    ़
    -0.07
    ang
    -0.07
    æĪĸ
    -0.06
    äºİ
    -0.06
    ëįĶëĿ¼êµ¬ìļĶ
    -0.06
    POSITIVE LOGITS
    件äºĭæĥħ
    0.09
    аÑĤÑĥ
    0.08
    åį«çĶŁç»Ħç»ĩ
    0.08
    家ä¼Ļ
    0.07
    å·¡è§Ĩåijĺ
    0.07
    że
    0.07
    è¦ģæ±Ĥèĩªå·±
    0.07
    æĺ¯è¦ģ
    0.07
    æĮĩçļĦ
    0.07
    ´Ī
    0.07
    Activations Density 0.016%

    No Known Activations