© 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. 58100
    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
    æľīä½į
    -0.07
    ulut
    -0.07
    CF
    -0.06
    æĹłåīį
    -0.06
    缺
    -0.06
     Alber
    -0.06
    encie
    -0.06
     Tew
    -0.06
    fass
    -0.06
    ½ij
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.08
    ä¸ľå±±
    0.08
    åĢ©
    0.07
    ansom
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    è¿Ļä¸ĢçĶŁ
    0.07
    PROTO
    0.07
    زÛĮ
    0.07
    hoto
    0.07
    ä¸į容忽è§Ĩ
    0.07
    Activations Density 0.000%

    No Known Activations