© 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. 55146
    Prev
    Next
    INDEX
    Explanations

    **bold markers** or `b` tags

    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
    Negative Logits
    ewa
    -0.08
    ebet
    -0.07
    åįĬæŃ¥
    -0.07
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.07
    aud
    -0.07
    èĭ¦ç»ĥ
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.06
    èĭ¦å¹²
    -0.06
     histórica
    -0.06
    edom
    -0.06
    POSITIVE LOGITS
    estad
    0.09
    å¾·å°Ķ
    0.07
    Õ¹
    0.07
    avourites
    0.07
    akta
    0.07
    ersions
    0.07
    otts
    0.07
    ç«ĭãģ¦
    0.06
    uers
    0.06
    uzzer
    0.06
    Activations Density 0.023%

    No Known Activations