© 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. 50635
    Prev
    Next
    INDEX
    Explanations

    financial deductions

    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
    æĸ°é«ĺ
    -0.08
    abet
    -0.08
    çĪĨæ£ļ
    -0.07
    entie
    -0.07
    mtree
    -0.07
    erce
    -0.07
    aves
    -0.07
    andes
    -0.07
    ä»·æł¼èµ°åĬ¿
    -0.07
    anford
    -0.07
    POSITIVE LOGITS
     removal
    0.10
     removes
    0.08
     remove
    0.08
    æİīçļĦ
    0.08
     Removal
    0.08
    æİī
    0.08
    移éĻ¤
    0.08
     weg
    0.08
    /remove
    0.08
     removing
    0.07
    Activations Density 0.032%

    No Known Activations