© 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. 7891
    Prev
    Next
    INDEX
    Explanations

    pressure-filling

    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
    n
    -0.07
    ee
    -0.07
    -0.06
    Âł
    -0.06
    x
    -0.06
     trag
    -0.06
    賦
    -0.06
    åĪ¶
    -0.06
    ĭ
    -0.05
    å°ĺ
    -0.05
    POSITIVE LOGITS
    å½Į
    0.08
    ĥĿ
    0.08
    åħĭç¦ı
    0.08
    conde
    0.08
    :path
    0.08
    纶
    0.08
    æĦıè§ģåıįé¦Ī
    0.08
    Ø®ÛĮ
    0.08
    ä»ħä»£è¡¨ä½ľèĢħ
    0.08
    OCI
    0.08
    Activations Density 0.001%

    No Known Activations