© 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. 62302
    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
     ballo
    -0.08
    åħ¶èĩªçĦ¶
    -0.07
    马åı¯
    -0.07
    ç¦ģæŃ¢è½¬è½½
    -0.07
    马åı¯æ³¢ç½Ĺ
    -0.07
    angat
    -0.07
    篩
    -0.07
    è§Ĩéķľ
    -0.07
     vot
    -0.07
    æ¼²
    -0.07
    POSITIVE LOGITS
     bonds
    0.09
    åħ¨æĸ°
    0.08
     bond
    0.08
    æĸ°
    0.07
    estruction
    0.07
    æĸ°æ¦Ĥ念
    0.07
    çĶĺ
    0.07
     newly
    0.07
    çŃīæĸ°
    0.07
    æĸ°çĶŁçļĦ
    0.07
    Activations Density 0.000%

    No Known Activations