© 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. 50949
    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
    ogle
    -0.08
    uert
    -0.08
    ewel
    -0.08
     nát
    -0.08
    å¾ĺ
    -0.07
    çĻ¾å·Ŀ
    -0.07
     berbasis
    -0.07
    uerte
    -0.07
    ampa
    -0.07
    ëĭĪëĭ¤
    -0.07
    POSITIVE LOGITS
    adius
    0.08
    没æľīåħ³ç³»
    0.07
    ugin
    0.07
    æİłè¿ĩ
    0.07
    äºĴ
    0.07
    nis
    0.06
    ptime
    0.06
    è¶ħè¿ĩ约
    0.06
     distance
    0.06
    æ¸ī
    0.06
    Activations Density 0.000%

    No Known Activations