© 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. 12344
    Prev
    Next
    INDEX
    Explanations

    roots, directory, _root, ancestral, starting point

    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
    bam
    -0.07
    æ°´çģ«
    -0.06
    å·¥ä½ľéĩįçĤ¹
    -0.06
    Ñĥй
    -0.06
    第äºĮ大
    -0.06
    wai
    -0.06
    itent
    -0.06
    occhi
    -0.06
    à¦ļà§į
    -0.06
    aption
    -0.06
    POSITIVE LOGITS
    æºIJ头
    0.15
    追溯åĪ°
    0.14
     underlying
    0.13
    追溯
    0.12
    溯æºIJ
    0.12
    åĽŀ溯
    0.12
    æºIJ头ä¸Ĭ
    0.11
     rewind
    0.10
    åİŁå§ĭçļĦ
    0.10
     ancestral
    0.10
    Activations Density 0.132%

    No Known Activations