© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    computed tomography reconstruction

    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
     ch
    -0.06
     pron
    -0.06
    ä»ĭ
    -0.06
     vag
    -0.06
     attr
    -0.06
     cas
    -0.06
     upt
    -0.06
    ä¸Ģæĭ³
    -0.06
    carb
    -0.06
    润æ»ij
    -0.06
    POSITIVE LOGITS
    éĩĩéĽĨ
    0.12
    æķ°æį®éĩĩéĽĨ
    0.09
    éĩĩ
    0.09
    éĩĩæł·
    0.09
    å°½æĶ¶
    0.09
     sampling
    0.09
     sweeps
    0.09
    Ñįм
    0.09
    æ¯ıä¸ĢæĿ¡
    0.09
     Sampling
    0.09
    Activations Density 0.114%

    No Known Activations