© 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. 49703
    Prev
    Next
    INDEX
    Explanations

    events or states of being

    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
    rast
    -0.07
    cident
    -0.07
    æł¹æį®éľĢè¦ģ
    -0.06
    à¸IJ
    -0.06
    itone
    -0.06
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    elier
    -0.06
    æĢ»æķ°çļĦ
    -0.06
     Dorf
    -0.06
    ãģµãĤĭ
    -0.06
    POSITIVE LOGITS
     acr
    0.07
    incontro
    0.06
     Broadcasting
    0.06
    onga
    0.06
    hay
    0.06
    以æѤæĿ¥
    0.06
    è°ļ
    0.06
    ardin
    0.06
    jm
    0.06
    ç¾½ç»Ĵ
    0.06
    Activations Density 0.060%

    No Known Activations