© 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. 19959
    Prev
    Next
    INDEX
    Explanations

    Karma yoga, sacrifice, serve, self-emptying

    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
    azol
    -0.08
    æĹº
    -0.07
    mid
    -0.06
    ä¸į容忽è§Ĩ
    -0.06
    è®¤çľŁç»Ħç»ĩ
    -0.06
    åĴ«å°º
    -0.06
    èĩªå°Ĭå¿ĥ
    -0.06
    หà¸Ļี
    -0.06
     mid
    -0.06
    ricos
    -0.06
    POSITIVE LOGITS
    æĹłä¸º
    0.09
    æīįèĥ½çľŁæŃ£
    0.09
    çĬ¶æĢģä¸ĭ
    0.08
    å¿ĺæİī
    0.08
    åİ»éĻ¤
    0.08
    æĹłèĻij
    0.08
    åį¸ä¸ĭ
    0.08
    顺åºĶ
    0.08
    çĬ¶æĢģ
    0.08
    è½»çĽĪ
    0.08
    Activations Density 0.021%

    No Known Activations