© 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. 1418
    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
    å®ĥå°±æĺ¯
    -0.07
    å±Ģå±Ģéķ¿
    -0.07
    å±Ģåī¯å±Ģéķ¿
    -0.07
    å®ĥ为
    -0.07
    ä¸įèĥ½è®©
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    çĭ±
    -0.06
     ngứa
    -0.06
    å®ĥ以
    -0.06
    amel
    -0.06
    POSITIVE LOGITS
    Ø«ÙĦ
    0.07
    baugh
    0.07
    \r
    0.07
    ombo
    0.07
    roach
    0.06
    å¿ĹåĪļ
    0.06
    een
    0.06
     Moreira
    0.06
    veld
    0.06
    tig
    0.06
    Activations Density 0.000%

    No Known Activations