© 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. 41661
    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
    èĻ«
    -0.08
    åĬŁ
    -0.07
    acun
    -0.07
     paral
    -0.07
    èŁ²
    -0.07
    lev
    -0.07
    antau
    -0.07
    rapper
    -0.06
     tal
    -0.06
     ta
    -0.06
    POSITIVE LOGITS
    eless
    0.08
    æ¸ħæ³ī
    0.07
    ãĥ¼ãĤº
    0.07
    ä¸Ĭä¸ĭçıŃ
    0.07
    éIJĺ
    0.07
     Sezione
    0.07
    others
    0.06
    ấu
    0.06
    rosa
    0.06
    èĩªè¡Į
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.