© 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. 13041
    Prev
    Next
    INDEX
    Explanations

    legal case citations and names

    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
    åĬĿ
    -0.07
    大çĪ·
    -0.07
    æ··ä¹±
    -0.06
    abus
    -0.06
    ulon
    -0.06
    å»ī
    -0.06
    ubl
    -0.06
    Ben
    -0.06
    ulo
    -0.06
    ulus
    -0.06
    POSITIVE LOGITS
    ocity
    0.08
    æŬ
    0.07
    onnier
    0.07
     tslint
    0.07
    æĻı
    0.07
     Tanner
    0.07
    以ä¸Ĭå°±æĺ¯
    0.07
     Dro
    0.07
    _-
    0.07
    nton
    0.07
    Activations Density 0.224%

    No Known Activations