© 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. 49420
    Prev
    Next
    INDEX
    Explanations

    underground structures and phenomena

    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
    èĻIJ
    -0.07
    å¦Ĥçģ«
    -0.07
     láng
    -0.07
    å¿ĥèĥ¸
    -0.07
    帧
    -0.07
    ÑģÑĤÑĢе
    -0.07
    gau
    -0.07
     Frames
    -0.07
    åĪĩãĤĮ
    -0.07
    çĩİ
    -0.07
    POSITIVE LOGITS
    åŁĭ
    0.16
     underground
    0.16
     buried
    0.15
     depths
    0.15
    åľ°ä¸ĭ
    0.15
    æ·±å¤Ħ
    0.14
     depth
    0.14
    æĮĸæİĺ
    0.14
    深度
    0.13
     deeper
    0.13
    Activations Density 0.149%

    No Known Activations