© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49382
    Prev
    Next
    INDEX
    Explanations

    listing items or options

    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
     outlaw
    -0.08
     Hv
    -0.07
    åıĬæŶè°ĥæķ´
    -0.07
     tore
    -0.07
    uable
    -0.07
    uj
    -0.07
    otal
    -0.07
    oute
    -0.06
    rovers
    -0.06
    æļĤ
    -0.06
    POSITIVE LOGITS
    æŀ¯çĩ¥
    0.10
    ç½ĹåĪĹ
    0.09
    å¼ıçļĦ
    0.08
    yron
    0.08
    stp
    0.08
    è½°çĤ¸
    0.08
    èĢĮæĺ¯
    0.08
     viva
    0.08
    æĹłæŃ¢
    0.07
    åįķè°ĥ
    0.07
    Activations Density 0.011%

    No Known Activations