© 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. 881
    Prev
    Next
    INDEX
    Explanations

    faults and errors

    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
    åIJİèĢħ
    -0.07
     latter
    -0.06
     Exped
    -0.06
    elsea
    -0.06
    ourd
    -0.06
    Ñĩан
    -0.06
    жан
    -0.06
    ÙĦÙĤ
    -0.06
    ordon
    -0.06
    ÑĤан
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.11
    ë¦ĩ
    0.08
    两çĶ¨
    0.08
    ´t
    0.07
    ogo
    0.07
    åħ¶äºĭ
    0.07
    次éĺħ读
    0.07
    schau
    0.07
    ogue
    0.07
    ablish
    0.07
    Activations Density 2.006%

    No Known Activations