© 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. 18414
    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
    vád
    -0.09
    asca
    -0.08
    天æĪIJ
    -0.08
    atlan
    -0.08
    assi
    -0.08
    olver
    -0.08
    (Unknown
    -0.07
    å°ij
    -0.07
    ÙĪسÙĬ
    -0.07
    onical
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥åĪ°
    0.07
     Gul
    0.07
    isseur
    0.07
    ä¸įéļ¾
    0.06
     Ot
    0.06
    对æľī
    0.06
    åŃ¦ä¹łçĶŁæ´»
    0.06
     bis
    0.06
     (*
    0.06
    éģį
    0.06
    Activations Density 0.000%

    No Known Activations