© 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. 31334
    Prev
    Next
    INDEX
    Explanations

    amber, RNA, vitamin, deaf

    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
    arella
    -0.09
    è§ij
    -0.08
    Putin
    -0.07
    laud
    -0.07
    该款
    -0.07
    èĸ«
    -0.07
    isex
    -0.07
    åĵĪèIJ¨åħĭæĸ¯åĿ¦
    -0.07
    rito
    -0.07
     thankfully
    -0.07
    POSITIVE LOGITS
    åľ¨å½ĵæŶ
    0.12
    å½ĵæŶ
    0.11
     seemed
    0.10
     mysterious
    0.10
    å½ĵæŶçļĦ
    0.09
    ç¥ŀç§ĺ
    0.09
    ç¥ŀç§ĺçļĦ
    0.09
     mystery
    0.08
    çķ¶æĻĤ
    0.08
     myster
    0.08
    Activations Density 0.074%

    No Known Activations