© 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. 24734
    Prev
    Next
    INDEX
    Explanations

    diagrams and structures

    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
     whatever
    -0.07
     whoever
    -0.07
    etty
    -0.07
    ulte
    -0.06
     Nhi
    -0.06
    ordio
    -0.06
    è´´çĿĢ
    -0.06
    çĽĸä¸Ĭ
    -0.06
     konusu
    -0.06
     contingency
    -0.06
    POSITIVE LOGITS
    éĥ¨åĪĨåĨħ容
    0.09
    abu
    0.09
    缸åħ³æĥħåĨµ
    0.09
    æľīåħ³æĥħåĨµ
    0.08
    ç»ĨèĬĤ
    0.08
     ilustr
    0.08
    çļĦéĥ¨åĪĨ
    0.08
    åıĬéĥ¨åĪĨ
    0.08
    éĥ¨åĪĨ
    0.08
     ЧаÑģÑĤÑĮ
    0.08
    Activations Density 0.057%

    No Known Activations