© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    illusion, projected, perceived, appear

    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
    éĵģè¡Ģ
    -0.09
    estre
    -0.08
    大è¿IJ
    -0.08
    æĬĵ
    -0.07
    Tokenizer
    -0.07
    othy
    -0.07
     Clean
    -0.07
     ÃĶn
    -0.07
     clean
    -0.07
    nerg
    -0.07
    POSITIVE LOGITS
     seolah
    0.11
     virtual
    0.09
    virtual
    0.09
     illusion
    0.09
    éĶĻè§ī
    0.08
     ảo
    0.08
    Virtual
    0.08
     Virtual
    0.08
     location
    0.08
    èĻļæĭŁ
    0.08
    Activations Density 0.014%

    No Known Activations