© 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. 51213
    Prev
    Next
    INDEX
    Explanations

    flexible and adaptable

    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
    ì°į
    -0.08
     móc
    -0.07
    รา
    -0.07
    izen
    -0.06
    ãģĹãģ£ãģĭãĤĬãģ¨
    -0.06
    åįıåĬĽ
    -0.06
    antal
    -0.06
    athan
    -0.06
    éģįéĩİ
    -0.06
    hlen
    -0.06
    POSITIVE LOGITS
    çģµæ´»
    0.10
    çģµæ´»çļĦ
    0.10
    èµ·è§ģ
    0.10
     léo
    0.09
    å¤ļåıĺ
    0.09
    andre
    0.09
    ueux
    0.09
    å¤ļæł·çļĦ
    0.09
    èĩªå¦Ĥ
    0.09
    ä½Ļåľ°
    0.09
    Activations Density 0.023%

    No Known Activations