© 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. 25631
    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
     inf
    -0.07
    _require
    -0.07
    èĢĮè¿ĩ
    -0.06
    è§ģéĿ¢
    -0.06
    cors
    -0.06
    缸å¾ħ
    -0.06
     coord
    -0.06
    wad
    -0.06
    åľ¨åį³
    -0.06
    çĥŁéħĴ
    -0.06
    POSITIVE LOGITS
    agate
    0.10
     оÑģÑĤаÑĤ
    0.10
    å¤ĦçIJĨåIJİ
    0.09
    ILLED
    0.08
    继ç»ŃåĬªåĬĽ
    0.08
    æ®ĺ
    0.08
    ä¸ĭä¸Ģ级
    0.08
    bookmark
    0.08
    æ®ĭ
    0.08
    ussen
    0.08
    Activations Density 0.000%

    No Known Activations