© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    field access and assignment

    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
    åIJİèĢħ
    -0.07
    åį³ä¾¿å¦ĤæѤ
    -0.07
    å°Ĩå®ĥ
    -0.07
     ensuing
    -0.07
    wo
    -0.07
    å°±è¿Ļæł·
    -0.07
    æľĢæĸ°åĬ¨æĢģ
    -0.07
    intang
    -0.07
    对åħ¶è¿Ľè¡Į
    -0.07
    åĪĻåı¯
    -0.07
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.08
    skr
    0.07
    å£ŀ
    0.07
    çŀ©
    0.07
    ä¸įèµ°
    0.07
    åľ¨åģļ好
    0.07
    è¦ģä¹Ī
    0.07
    utz
    0.07
    unk
    0.07
    avel
    0.07
    Activations Density 0.200%

    No Known Activations