© 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. 55223
    Prev
    Next
    INDEX
    Explanations

    long-term care, autoimmune hepatitis, lizard penis

    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
     mÃł
    -0.07
    бал
    -0.06
    åİĺ
    -0.06
    æ®Ĩ
    -0.06
    为ä¸Ńå¿ĥçļĦ
    -0.06
     t
    -0.06
     ÙħÛĮÙĦ
    -0.06
    wel
    -0.06
    åĽ
    -0.06
    stå
    -0.05
    POSITIVE LOGITS
    ukt
    0.08
    ontro
    0.08
    è°ĥæŁ¥åıijçİ°
    0.08
    abouts
    0.08
    amarca
    0.08
    landa
    0.08
    ancar
    0.08
    ardt
    0.08
    vero
    0.08
    anzo
    0.08
    Activations Density 0.144%

    No Known Activations