© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    digits can be anywhere

    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
    麽
    -0.08
    称ä¹ĭ为
    -0.08
    memcpy
    -0.08
    _MAY
    -0.08
    ä»İæĶ¿
    -0.07
    à¹Ģรียà¸ģวà¹Īา
    -0.07
    å®Ľ
    -0.07
     ('$
    -0.07
    cher
    -0.06
    eiros
    -0.06
    POSITIVE LOGITS
     either
    0.08
    ä»Ģä¹Īåij¢
    0.08
    éĶĻ误æĪĸ
    0.08
     anything
    0.07
    åIJ«
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    以ä¸ĭåĩł
    0.07
    åĽ¾çīĩæĪĸ
    0.07
    å°ıåĪ°
    0.07
    ected
    0.06
    Activations Density 0.008%

    No Known Activations