© 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. 45447
    Prev
    Next
    INDEX
    Explanations

    interest rates, mortgage, and tax 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
    å³¥
    -0.07
    VN
    -0.07
    schap
    -0.07
     functions
    -0.06
    æĽľ
    -0.06
    æºĸ
    -0.06
    çī¹å®ļçļĦ
    -0.06
    éĴ¦
    -0.06
    Desc
    -0.06
     nowadays
    -0.06
    POSITIVE LOGITS
     calculated
    0.10
    å®ŀéĻħéľĢè¦ģ
    0.09
    å®ŀéĻħ
    0.09
     theoretical
    0.09
    çĻ½è´¹
    0.08
     realistically
    0.08
    actual
    0.08
    ampa
    0.08
    akeup
    0.08
    çĪ¬åĿ¡
    0.08
    Activations Density 0.001%

    No Known Activations