© 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. 55242
    Prev
    Next
    INDEX
    Explanations

    cause cancer or toxicity

    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
     respek
    -0.08
    女åħĴ
    -0.08
    åIJ«ç³ĸ
    -0.08
     mastur
    -0.08
    åħĭéļ¾
    -0.08
    女åĦ¿
    -0.08
    ctor
    -0.07
    leman
    -0.07
     consol
    -0.07
    .Dynamic
    -0.07
    POSITIVE LOGITS
    omm
    0.07
     severe
    0.07
    严éĩįçļĦ
    0.07
     serious
    0.07
    åĬŁ
    0.07
     permanent
    0.07
    ç§ijåѦçłĶ究
    0.06
    ä¼ļéĢłæĪIJ
    0.06
     reproductive
    0.06
    ÏĦια
    0.06
    Activations Density 0.126%

    No Known Activations