© 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. 51741
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸įèĻļ
    -0.08
    addon
    -0.08
    æłĸ
    -0.08
    alami
    -0.08
     *(*
    -0.08
    hton
    -0.07
    åħ¶éģĵ
    -0.07
    QUARE
    -0.07
    ä½łåĪ°åºķ
    -0.07
    ettle
    -0.07
    POSITIVE LOGITS
    abee
    0.08
    olut
    0.07
    _idle
    0.06
    æ¯Ķè¾ĥç®Ģåįķ
    0.06
    inkin
    0.06
    space
    0.06
    quired
    0.06
    plain
    0.06
     idle
    0.06
    å¾Īç®Ģåįķ
    0.06
    Activations Density 0.000%

    No Known Activations