© 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. 55313
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ç¾ļ
    -0.10
    plr
    -0.08
     iepazÄ«Å¡anÄģs
    -0.08
    иÑĤаÑĢ
    -0.08
     revan
    -0.08
     Insg
    -0.08
    è¿Ľä¸ĢæŃ¥è§ĦèĮĥ
    -0.07
    è¯¥ä½ľèĢħ
    -0.07
    onton
    -0.07
    .mdl
    -0.07
    POSITIVE LOGITS
    åĢĴæķ°
    0.08
     conce
    0.06
    cube
    0.06
    æĸIJ
    0.06
    æĸ¹éĺµ
    0.06
    ç»ĦæĪIJ
    0.06
    CCCCCC
    0.06
     näm
    0.06
    ÙĨاÙĨ
    0.05
    yling
    0.05
    Activations Density 0.003%

    No Known Activations