© 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. 47917
    Prev
    Next
    INDEX
    Explanations

    code snippets with `+` or `(`

    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
    ampo
    -0.08
    att
    -0.07
    Att
    -0.07
    -filter
    -0.06
     Att
    -0.06
    gom
    -0.06
    åĴĮåIJĮåѦ
    -0.06
    å¾ģæ±ĤæĦıè§ģ稿
    -0.06
    oner
    -0.06
    ä¸İçİ°å®ŀ
    -0.06
    POSITIVE LOGITS
    +len
    0.10
    æĬµ
    0.08
    +n
    0.08
    +(\
    0.08
    +offset
    0.08
    ิà¸ļ
    0.08
    nds
    0.07
     -$
    0.07
    thood
    0.07
    TES
    0.07
    Activations Density 0.054%

    No Known Activations