© 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. 57476
    Prev
    Next
    INDEX
    Explanations

    arterial stiffness, event, advice, control, protest, evaluation

    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
    å°½åħ¶
    -0.06
    roc
    -0.06
    maf
    -0.06
    ħ
    -0.06
    /notification
    -0.06
    ç¨İ
    -0.06
    æĪĸéĿŀ
    -0.06
    /xhtml
    -0.06
    ÙĦÙĬÙĪÙĨ
    -0.06
    éļ¨
    -0.06
    POSITIVE LOGITS
    åīįè¿°
    0.08
    设为
    0.07
    żej
    0.07
    å¦Ĥä¸Ĭ
    0.07
    ä¸Ĭè¨ĺ
    0.07
    ä¸Ĭè¿°
    0.07
    BS
    0.06
     above
    0.06
    ÙĤص
    0.06
     Gutsche
    0.06
    Activations Density 0.033%

    No Known Activations