© 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. 25993
    Prev
    Next
    INDEX
    Explanations

    legal requirements and obligations

    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
    á»ijt
    -0.08
     geopol
    -0.07
    rush
    -0.07
     Haven
    -0.07
    èĩªå·±éĥ½
    -0.07
    嵩
    -0.07
     nanti
    -0.07
    Ùİار
    -0.07
    æĪĸåĪłéĻ¤
    -0.07
    çł´èİ·
    -0.07
    POSITIVE LOGITS
     guarantee
    0.09
    è¦ģæ±Ĥ
    0.09
    requ
    0.08
    è¦ģæ±Ĥåľ¨
    0.08
    è§Ħå®ļçļĦ
    0.08
    è§Ħå®ļäºĨ
    0.08
    è¦ģæ±ĤçļĦ
    0.08
    èµĭäºĪ
    0.08
     requiring
    0.08
     requires
    0.07
    Activations Density 0.085%

    No Known Activations