© 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. 37708
    Prev
    Next
    INDEX
    Explanations

    journal citations and references

    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
    æĵį
    -0.07
    çĶ
    -0.07
    ÃŃs
    -0.07
    çĻ¾åIJį
    -0.07
    çĶļèĩ³æ¯Ķ
    -0.07
    enus
    -0.06
    尽管
    -0.06
     bá»ĵ
    -0.06
    ÑıÑģ
    -0.06
    ]")
    -0.06
    POSITIVE LOGITS
    igham
    0.08
    纵横
    0.07
    amu
    0.07
    .case
    0.07
    dle
    0.07
    大ä¸ĸçķĮ
    0.07
    кеÑĢа
    0.07
    division
    0.07
    κι
    0.07
     division
    0.06
    Activations Density 0.060%

    No Known Activations