© 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. 3544
    Prev
    Next
    INDEX
    Explanations

    JC Penney department store

    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
     Zit
    -0.08
    zit
    -0.07
    жеÑĢ
    -0.07
    euse
    -0.07
    _die
    -0.07
     cru
    -0.07
    å°±æĺ¯æĪijçļĦ
    -0.07
    urlencode
    -0.07
    RUN
    -0.07
    ä¸ĭä¸ĢåĪ»
    -0.07
    POSITIVE LOGITS
    ä¸įä¸Ģå®ļ
    0.09
    åľ¨æŁIJäºĽ
    0.08
    åıĮéĩį
    0.08
    ä¸įä¸Ģå®ļæĺ¯
    0.07
    æľªå¿ħ
    0.07
    adox
    0.07
    æľī两ç§į
    0.07
    à¸Ńิสระ
    0.07
    åįİéĺ³
    0.07
     strangely
    0.07
    Activations Density 0.521%

    No Known Activations