© 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. 39305
    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
    ä¸ĩå¥Ĺ
    -0.07
     Caz
    -0.07
    ç»ĦæĪIJåijĺ
    -0.06
     anon
    -0.06
     Sesso
    -0.06
    æĻºåķĨ
    -0.06
    对çĹĩæ²»çĸĹ
    -0.06
    MS
    -0.06
    anon
    -0.06
    æľĪèĩ³ä»Ĭ
    -0.06
    POSITIVE LOGITS
    bere
    0.08
    claimed
    0.07
    为æŃ¢
    0.07
     бÑĥдÑĤо
    0.07
    è¿Ļ并ä¸įæĺ¯
    0.06
    æī
    0.06
    adium
    0.06
    åIJĪæĪIJ
    0.06
    åĬłæĭ¿å¤§
    0.06
    æĶ
    0.06
    Activations Density 0.000%

    No Known Activations