© 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. 20253
    Prev
    Next
    INDEX
    Explanations

    citations in academic papers

    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
    ТС
    -0.08
    kje
    -0.08
    ')+
    -0.08
    .RES
    -0.08
    )==
    -0.08
     Mercato
    -0.08
    +len
    -0.08
    )>>
    -0.08
    HTTPRequest
    -0.07
    ']+
    -0.07
    POSITIVE LOGITS
    Remark
    0.08
     guarantees
    0.06
     pp
    0.06
    aper
    0.06
    Remarks
    0.06
    cev
    0.06
     Remark
    0.06
    (
    0.06
    inter
    0.06
    åĩĨ
    0.06
    Activations Density 0.043%

    No Known Activations