© 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. 28079
    Prev
    Next
    INDEX
    Explanations

    question starters (do, does)

    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
    rotein
    -0.07
    ÙĨاÙĨ
    -0.07
    äºĨä¸Ģ大æī¹
    -0.06
    revet
    -0.06
    datepicker
    -0.06
    ?key
    -0.06
    èĩ³å°ij
    -0.06
    xies
    -0.06
    ØŃ
    -0.06
    FileManager
    -0.06
    POSITIVE LOGITS
     betreft
    0.10
     happen
    0.08
    éľĢè¦ģä»Ģä¹Ī
    0.08
     ÙĪÙħا
    0.08
    çļĦæĺ¯ä»Ģä¹Ī
    0.08
     happened
    0.08
    ä¹ĭæīĢ
    0.07
    geler
    0.07
     пÑĢоиÑģ
    0.07
    ç»Ļä½łçļĦ
    0.07
    Activations Density 0.154%

    No Known Activations