© 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. 64328
    Prev
    Next
    INDEX
    Explanations

    research studies and modifications

    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
    éĥ½æĹłæ³ķ
    -0.10
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.09
    éĥ½å¿ħé¡»
    -0.08
    éĥ½ä¸įèĥ½
    -0.08
    éĥ½èĥ½å¤Ł
    -0.08
    éĥ½å·²
    -0.08
    éĥ½å¼Ģå§ĭ
    -0.08
    éĥ½åĥı
    -0.08
    éĥ½æ²¡
    -0.07
    olley
    -0.07
    POSITIVE LOGITS
     follows
    0.09
     involves
    0.09
     includes
    0.08
    åħ³éĶ®åľ¨äºİ
    0.08
    çļĦåħ³éĶ®
    0.08
     consists
    0.08
    å®ĮæĪIJåIJİ
    0.08
     is
    0.08
     also
    0.07
    主è¦ģåĮħæĭ¬
    0.07
    Activations Density 0.109%

    No Known Activations