© 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. 56318
    Prev
    Next
    INDEX
    Explanations

    code or indexing with 'business'

    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
    åĸĥ
    -0.07
    amol
    -0.07
    ä¹ĭå®Ŀ
    -0.07
     mod
    -0.07
    çĽħ
    -0.07
    stub
    -0.06
    bones
    -0.06
    ces
    -0.06
    éĢIJ级
    -0.06
    solid
    -0.06
    POSITIVE LOGITS
    æ¤
    0.08
    æ¥
    0.08
    æİ©
    0.07
    ä¸ĩä¸Ī
    0.07
    å®
    0.07
    etzen
    0.07
    yped
    0.07
    essus
    0.07
    oger
    0.07
    åħĭ鼷
    0.07
    Activations Density 0.007%

    No Known Activations