© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44875
    Prev
    Next
    INDEX
    Explanations

    condense/condenser/condensation

    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
    éļĪ
    -0.07
    æī¯
    -0.07
    红æ¢ħ
    -0.07
    åģ¥åº·ç½ij
    -0.07
    fad
    -0.06
    ebas
    -0.06
    esture
    -0.06
    ÙĴÙĨ
    -0.06
    缸åħ³éĺħ读
    -0.06
    åģ¥åº·éĹ®é¢ĺ
    -0.06
    POSITIVE LOGITS
    åĽŀæµģ
    0.12
    ä¸ĭæĿ¥çļĦ
    0.09
    åĨ·åį´
    0.09
    åĽŀæĿ¥çļĦ
    0.08
    erber
    0.08
     catcher
    0.08
     cooled
    0.08
    循çݯ
    0.08
    转åĮĸçļĦ
    0.08
     return
    0.07
    Activations Density 0.007%

    No Known Activations