© 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. 64705
    Prev
    Next
    INDEX
    Explanations

    firmware implementation

    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
    竹
    -0.07
     homes
    -0.06
    äºı
    -0.06
    竹åŃIJ
    -0.06
    ivalence
    -0.06
    ICT
    -0.06
    æľĶ
    -0.06
    åİĨåı²æĢ§
    -0.06
    URI
    -0.06
    涯
    -0.06
    POSITIVE LOGITS
    _IMPLEMENT
    0.09
     gấp
    0.08
    _USAGE
    0.08
    ä¸ĩåıª
    0.08
    peria
    0.08
    _datas
    0.08
    èĬ³èįī
    0.08
    AGER
    0.08
    uai
    0.07
    èĥ½å¹²
    0.07
    Activations Density 0.085%

    No Known Activations