© 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. 23745
    Prev
    Next
    INDEX
    Explanations

    suggesting or indicating improvement

    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
     möglichst
    -0.08
    å°½æĥħçļĦ
    -0.07
    lest
    -0.07
    DOMNode
    -0.07
    åıįæŃ£
    -0.07
    OnError
    -0.07
    @js
    -0.07
    оÑĢÑĤи
    -0.07
    trys
    -0.07
    "value
    -0.07
    POSITIVE LOGITS
    è¿Ļ表æĺİ
    0.14
    è¿Ļ说æĺİ
    0.13
    表æĺİ
    0.11
     suggesting
    0.11
    说æĺİ
    0.11
    suggest
    0.11
    uggest
    0.10
     suggests
    0.10
     suggest
    0.10
    æļĹ示
    0.08
    Activations Density 0.478%

    No Known Activations