© 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. 62532
    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
    <|box_end|>
    -0.07
    ("__
    -0.07
    ili
    -0.07
    again
    -0.07
    å¾Īæ·±
    -0.06
    æĬĬ
    -0.06
    eneric
    -0.06
    IfNeeded
    -0.06
    .dat
    -0.06
    “My
    -0.06
    POSITIVE LOGITS
    æĸ°ç½ij
    0.09
    alba
    0.08
    phia
    0.08
    eksi
    0.08
    æºIJåİ¿
    0.08
    ä¸ĩä½Ļåħĥ
    0.08
    å¸Ĥ缴
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹
    0.07
    undra
    0.07
    è¾Ľèĭ¦äºĨ
    0.07
    Activations Density 0.000%

    No Known Activations