© 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. 18472
    Prev
    Next
    INDEX
    Explanations

    Carter, Table, weight, robust, sequence

    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
    LOG
    -0.07
    eli
    -0.07
    è°ĵè¯Ń
    -0.07
     substr
    -0.07
    èµ·ä¹ī
    -0.06
     Registers
    -0.06
    egrity
    -0.06
    HEMA
    -0.06
    æĢ§åij½
    -0.06
    èĬ±èī²
    -0.06
    POSITIVE LOGITS
    -anchor
    0.08
     Frei
    0.07
    ®
    0.07
    åĪĢåŃIJ
    0.07
    éĺµ
    0.07
     اÙĦاØŃ
    0.07
    enity
    0.07
    à¸Ļาà¸Ļ
    0.07
    иÑģка
    0.06
    ç¥ŀæĢ¡
    0.06
    Activations Density 0.002%

    No Known Activations